WO2007044422A2 - An automated system and method for distinguishing audio signals received in response to placing an outbound call - Google Patents
An automated system and method for distinguishing audio signals received in response to placing an outbound call Download PDFInfo
- Publication number
- WO2007044422A2 WO2007044422A2 PCT/US2006/038840 US2006038840W WO2007044422A2 WO 2007044422 A2 WO2007044422 A2 WO 2007044422A2 US 2006038840 W US2006038840 W US 2006038840W WO 2007044422 A2 WO2007044422 A2 WO 2007044422A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- audio content
- audio
- characteristic
- content
- response
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5158—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with automated outdialling systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
- H04M2201/10—Logic circuits
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2203/00—Aspects of automatic or semi-automatic exchanges
- H04M2203/20—Aspects of automatic or semi-automatic exchanges related to features of supplementary services
- H04M2203/2027—Live party detection
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/42017—Customized ring-back tones
Definitions
- TITLE An Automated System and Method for Distinguishing Audio
- the present invention relates to distinguishing audio signals received in response to placing an outbound call and, more particularly, to an automated system and method for analyzing the audio signal and taking one of a plurality of actions based on a characteristic of the audio signal.
- Automated dialing systems are often used to place telephone calls and then connect the called party to a resource only after the called party has answered the telephone.
- An advantage of using an automated dialing system is that the resource is not expended manually dialing the call and waiting for the called party to answer the telephone. Further, if the line is busy or the called party does not answer the telephone after a predetermined number of rings - no resource time is expended on the unanswered call.
- One problem with automated dialing systems is that if an answering machine answers the call, the resource may be connected to the answering machine rather than the called party.
- US Patent 5,371 ,787 to Hamilton uses a combination of a click detector, a ring detector, a voice detector, click analyzer, ring analyzer, noise analyzer, answer analyzer, silence analyzer, and voice analyzer to distinguish whether a telephone was answered by an answering machine based on time intervals of voice and silence within the audio signal.
- US Patents 5,430,792 to Jesurum et al., US Patent 5,724,420 to Torgrim, and US Patent 5,828,731 to Szlam et al. similarly distinguishes between the existence of voice and silence within the audio signal to determine whether the telephone has been answered by an answering machine.
- traditional ring back e.g. a cadence of 2 seconds on, 4 seconds off in the US
- customized ring back audio content can be any recorded audio such as a spoken message, music, a performed audio monolog (such as comedy), or other recorded audible sound.
- Replacing the traditional ring back cadence with audio content eliminates an easily detectible sequence of events within the audio signal (the transitions between ring and silence) that is used by traditional systems to: i) detect answering of the telephone; and ii) initiate the measurement of time elapsing between the audio discontinuities of voice and silence used as input for the algorithms for determining whether the call was answered by a person or an answering machine.
- what is needed is a system and method for distinguishing audio signals received in response to placing an outbound call and, more particularly, to an automated system and method for analyzing audio content (as opposed to discontinuities in the audio signal) and taking one of a plurality of actions based on a characteristic or set of characteristics of the audio signal.
- what is needed is a system and method for detecting when an outbound telephone call has been answered in response to placing an outbound call that does not rely on detecting traditional ring back cadence.
- a first aspect of the present invention comprises an action direction system for directing action based on distinguishing audio content received in response to placing an outbound call.
- the system comprises an audio signal analysis system and an audio content analysis system.
- the audio signal analysis system directs a portion of an audio signal that comprises audio content to the audio content analysis system.
- the audio content analysis system i) receives portions of the audio signal comprising audio content; and ii) directs handling of the outbound call in response to detecting a characteristic of the audio content.
- the audio content analysis system i) directs a first handling of the outbound call in response to identifying a first characteristic of the audio content; and ii) directs a second handling of the outbound call in response to identifying a second characteristic of the audio content.
- the first handling of the outbound call may be directed in response to identifying a characteristic of the audio content associated with recorded content and the second handling of the outbound call may be directed in response to identifying a characteristic of the audio content associated with real time spoken audio.
- the characteristic of the audio content that is associated with recorded audio content may be a repetitive measure (such as music) or the characteristic of the audio content that is associated with recorded audio may be an extraneous intensity/frequency spectrum pattern (e.g. outside a recognizable voice intensity/frequency spectrum pattern).
- a handling system may direct handling of the outbound call in response to a combination of signal direction provided by the audio signal analysis system and a content direction provided by the audio content analysis system.
- the signal direction provided by the audio signal analyses system may identify a portion of the audio signal representing audio content and a portion of the audio signal representing events from a group of signal events consisting of: i) binary ring cadence; ii) binary busy cadence; iii) an "off hook" transition click; and iv) audio below a silence threshold.
- the content direction provided by the audio content analysis identifies a characteristic of the audio content.
- the handling system may: i) direct a first handling of the outbound call in response to the content direction identifying a first characteristic of the audio content; and ii) direct a second handling of the outbound call in response to the content direction identifying a second characteristic of the audio content.
- the handling system may: i) direct handling of the outbound call as unanswered in a ring back state in response to identifying a characteristic of the audio content associated with recorded content before the audio signal analysis system identifies a portion of the audio signal consisting of binary ring cadence; ii) direct handling of the outbound call as answered by a messaging machine in response to identifying a characteristic of the audio content associated with recorded content after the audio signal analysis system identifies a portion of the audio signal consisting of binary ring cadence or an "off hook" transition click; and iii) direct handling of the outbound call answered by a person in response to identifying a characteristic of the audio content associated with real time spoken audio.
- the characteristic of the audio content that is associated with recorded audio content may be a repetitive measure (such as music) or the characteristic of the audio content that is associated with recorded audio may be an extraneous intensity/frequency spectrum pattern (e.g. outside a recognizable voice intensity/frequency spectrum pattern).
- a second aspect of the present invention comprises a system for detecting audio content ring back in response to placing an outbound call.
- the system comprises an audio signal analysis system and an audio content analysis system.
- the audio signal analysis system directs a portion of an audio signal that comprises audio content to an audio content analysis system in response to detecting such audio content before detecting a portion of an audio signal that comprises binary ring back cadence.
- the audio content analysis system i) receives portions of the audio signal comprising audio content; and ii) identifies the portion of the audio signal comprising audio content as audio content ring back if a characteristic of the audio content is associated with recorded audio content.
- the characteristic of the audio content that is associated with recorded audio content may be a repetitive measure (such as music) or the characteristic of the audio content that is associated with recorded audio may be an extraneous intensity/frequency spectrum pattern (e.g. outside a recognizable voice intensity/frequency spectrum pattern).
- Figure 1 is a block diagram representing an exemplary architecture for an action direction system for directing action based on analysis of audio content within an audio signal in accordance with one embodiment of the present invention
- Figure 2 is a table representing exemplary audio content characteristics and associated secondary characteristics in accordance with one embodiment of the present invention
- Figure 3 is a table representing exemplary event parameters in the context of placing an outbound call and a direction output associated therewith in accordance with one embodiment of the present invention.
- Figure 4 is a block diagram representing exemplary implementation of a system for direction action based on analysis of audio content in an automated dialing system. Detailed Description of the Exemplary Embodiments
- each element with a reference number is similar to other elements with the same reference number independent of any letter designation following the reference number.
- a reference number with a specific letter designation following the reference number refers to the specific element with the number and letter designation and a reference number without a specific letter designation refers to all elements, with the same reference number independent of any letter designation following the reference number in the drawings.
- FIG. 1 represents an overview of an action direction system 10 for directing action based on analyzing an audio content portion of an audio signal 14 (e.g audio content 15) received in response to placing an outbound call.
- the action direction system 10 receives an audio signal 14 from the telephony network 12 in response to placement of an outbound call - typically placed by an automated dialing system.
- the action direction system 10 may comprise an audio signal analysis system 16, an audio content analysis system 20, and a handling system 26. It should be appreciated that the grouping of functions performed by each of the audio signal analysis system 16, the audio content analysis system 20, and the handling system 26 is for purposes of facilitating teaching of the present invention herein and those skilled in the art will recognize that in any embedded system the grouping of functions is a matter of design choice.
- the audio signal analysis system 16 uses known systems to analyze the audio signal 14 to distinguish between portions of the audio signal 14 which represent i) in-band signaling such as binary ring cadence and binary busy cadence; ii) an off-hook transition click; iii) audio below a silence threshold; and iv) audio content.
- Audio content 15 comprises a portion of the audio signal 14, other than in-band signaling, with a varying intensity and frequency above a silence threshold which, when converted to acoustic sound, has significance to a person, typically linguistic significance (such as spoken words) or musical significance (such as sung words and/or musical instruments).
- a signal direction 22 provides a signal direction to the handling system 26 identifying each such portion of the audio signal 14 and may provide an audio content direction 18 to the audio content analysis system 20 identifying the portion(s) of the audio signal 14 representing audio content 15.
- the audio content direction 18 (identifying of the portion(s) of the audio signal representing audio content) may itself contain the audio content 15 or the portion of the audio signal 14 representing the audio content 15.
- the audio content analysis system 20 receives the portions of the audio signal 14 comprising audio content 15 and directs handling of the outbound call by detecting a characteristic of the audio content 15 and providing a content direction 24 identifying the characteristic (or associated characteristic) of the audio content 15 to the handling system 26.
- the audio content analysis system 20 may comprise known digital signal processing systems, narrow band filters, and pattern matching algorithms for identifying and distinguishing between characteristics of the audio content.
- a characteristic 42 includes repetitive measure (characteristic 42a) such as musical rhythm or beat detected within the intensity pattern and frequency spectrum (e.g. the intensity/frequency spectrum) of the portion of the audio signal 14 representing audio content 15.
- the associated characteristic 44 associated with a repetitive measure 42a is recorded content 44a because, within the context of answering a telephone call, music is typically modulated onto the phone line audio signal 14 by a machine that plays a recording such as an answering machine, voice mail, or a ring back content server. Music is rarely performed live at the answering of a telephone.
- a characteristic 42 includes an extraneous intensity/frequency spectrum (characteristic 42b).
- Human speech typically has a recognizable intensity and frequency spectrum (e.g. S. S. I. F. S or speech shaped intensity/frequency spectrums). Audio content with an intensity and/or frequency spectrum that is outside of the speech shaped intensity/frequency spectrum and above a hiss threshold is, for purposes of this application, referred to as an extraneous intensity/frequency spectrum pattern.
- the associated characteristic 44 associated with an extraneous intensity/frequency spectrum 42b is recorded content 44a because, within the context of answering a telephone call, audio content other than audio content dominated by human speech is typically modulated onto the phone line by a machine that plays a recording such as an answering machine, voice mail, or a ring back content server.
- extraneous intensity/frequency may include laughter or applause within a recording of a spoken performance such as that of a comedian.
- a characteristic 42 includes a speech shaped intensity/frequency spectrum - lasting for an extended duration (on the order of two seconds or more) from its start (e.g. a continuous speech shaped intensity/frequency spectrum 42c of an extended duration).
- the associated characteristic 44 associated with continuous speech shaped intensity/frequency spectrum 42c of an extended duration is recorded content 44a because in the context of answering a telephone, human speech that continues without a pause for a return greeting of 350ms to 2,000 ms is typically associated with a pre-recorded announcement rather than a human making a greeting and pausing for a return greeting (e.g. a return greeting pause).
- a characteristic 42 includes a speech shaped intensity/frequency spectrum - with a repetitive pattern (e.g. a repetitive speech shaped intensity/frequency spectrum 42d).
- the associated characteristic 44 associated with repetitive speech shaped intensity/frequency spectrum 42d is real time spoken audio 44b because, within the context of answering a telephone, human speech that repeats one or more words (with a return greeting pause there between) is a characteristic of a human speaking a greeting, expecting a response, and repeating the greeting if no response is forth coming.
- a characteristic 42 includes a discontinuity 42e in the intensity/frequency spectrum.
- the associated characteristic 44 associated with discontinuity 42e in the intensity/frequency spectrum is an answer event 44c because, within the context of answering a telephone, a discontinuity 42e is a characteristic of the change in audio content associated with a human "taking over" from machine generated audio content such as when a person answers the telephone in the middle of an answering machine greeting or answers the telephone in the middle of audio content ring back.
- the handling system 26 receives the signal direction 22 from the audio signal analysis system 16 and receives the content direction 24 from the audio content analysis system 20 and directs handling of the outbound call in response thereto by generating a direction output 28.
- FIG. 3 a table representing exemplary handling in response to an event parameter 46 (e.g. various permutations of the signal direction 22 and the content direction 24) is shown.
- event parameter 46 e.g. various permutations of the signal direction 22 and the content direction 24
- an event parameter 46a the presence of binary busy cadence within the audio signal 14 is associated with direction output 28a to handle the present status of the outbound call as unanswered and busy.
- an event parameter 46b the presence of audio content 15 within the audio signal 14 with a characteristic 42 associated with recorded content 44a (both of Figure 2) before the existence of binary ring back cadence within the audio signal 14 can be interpreted as audio content ring back and the direction output 28b is a direction to maintain a ring back state (e.g. handle the present status of the outbound call as in a ring back state).
- an event parameter 46c the presence of binary ring back cadence within the audio signal 14 followed by audio content 15 ' within the audio signal 14 with a characteristic 42 associated with recorded content 44a (both of Figure 2) can be interpreted as recorded audio content from an answering machine or voice mail server and the direction output 28c is a direction to handle the present status of the outbound call as answered by a machine.
- an event parameter 46d the presence of an off- hook transition click within the audio signal 14 followed by audio content 15 within the audio signal 14 with a characteristic 42 associated with recorded content 44a (both of Figure 2) can be interpreted as recorded audio content from an answering machine or voice mail and the direction output 28c is a direction to handle the present status of the outbound call as answered by a machine.
- the presence of audio content 15 within the audio signal 14 with a characteristic 42 associated with real time spoken audio 44b can be interpreted as human speech and the direction output 28d is a direction to handle the present status of the outbound call as answered by a person.
- an event parameter 46f the presence of audio content 15 within the audio signal 14 (which may be ambiguous as to whether recorded content of real time spoken audio), followed by audio below a silence threshold lasting between 350 ms and 2,000ms, followed by audio content 15 (again, which may be ambiguous as to whether recorded content of real time spoken audio) which, in the aggregate represents a repetitive speech shaped intensity/frequency spectrum (42d of Figure 2) can be interpreted as human speech and the direction output 28d is a direction to handle the present status of the outbound all as answered by a person.
- the block diagram of Figure 4 represents an exemplary implementation of the action direction system 10 within an automated dialing system 30.
- the automated dialing system 30 couples to the telephone network 12 for placing outbound calls.
- the automated dialing system 30 may also be coupled to any of an interactive voice response (IVR) system 48, a recorded message system 50, and a local telephone network 32 for handling of the outbound calls once answered.
- IVR interactive voice response
- an outbound call after being answered, may be coupled to the IVR system 42 for automated interaction with the called party, coupled to the recorded message system 44 for playing a message to the called party, or coupled to a service representative 34 over the local telephone network 32 for service representative interaction with the called party.
- the automated dialing system 30 comprises an outbound call placement system 36 and the action direction system 10.
- the outbound call placement system 36 comprises an automated handling system 40 and a service representative connection system 38.
- the audio signal is coupled to the action direction system 10 which, in turn, provides a direction output signal 28 to the automated handling system 40. If and when the direction output signal 28 indicates that the outbound call is in an answered by a person state: i) the automated handling system 40 may couple the outbound call to the IVR system 48 or the recorded message system 50; or ii) the service representative connection system 38 may couple the outbound call to a service representative 34.
- systems and methods of the present invention provide for: i) distinguishing audio received in response to placing an outbound call by analyzing audio content within an audio signal (as opposed to detecting discontinuities in the audio signal) and taking one of a plurality of actions based on a characteristic of the audio signal; ii) detecting when an outbound telephone call has been answered in response to placing an outbound call that does not rely on detecting traditional ring back cadence; iii) detecting whether an outbound telephone call has been answered in a network lacking traditional ring back cadence; and iv) if answered, whether such outbound call has been answered by a person or an answering machine.
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Telephonic Communication Services (AREA)
- Radio Relay Systems (AREA)
Abstract
A system (10) directs action based on distinguishing audio content received in response to placing an outbound call. The system comprises an audio signal analysis system (16) and an audio content analysis system (20). The audio signal analysis system (16) directs (18) a portion of an audio signal (14) that comprises audio content (15) to the audio content analysis system (20). The audio content analysis system (20): i) receives portions of the audio signal comprising audio content (15); and ii) directs handling (28) of the outbound call in response to detecting a characteristic (42) of the audio content. The audio content system (20): i) directs a first handling of the outbound call in response to identifying a first characteristic of the audio content; and ii) directs a second handling of the outbound call in response to identifying a second characteristic of the audio content.
Description
TITLE: An Automated System and Method for Distinguishing Audio
Signals Received in Response to Placing an Outbound Call.
Technical Field
The present invention relates to distinguishing audio signals received in response to placing an outbound call and, more particularly, to an automated system and method for analyzing the audio signal and taking one of a plurality of actions based on a characteristic of the audio signal.
Background Art
Automated dialing systems are often used to place telephone calls and then connect the called party to a resource only after the called party has answered the telephone. An advantage of using an automated dialing system is that the resource is not expended manually dialing the call and waiting for the called party to answer the telephone. Further, if the line is busy or the called party does not answer the telephone after a predetermined number of rings - no resource time is expended on the unanswered call.
One problem with automated dialing systems is that if an answering machine answers the call, the resource may be connected to the answering machine rather than the called party.
To alleviate this problem, several systems have been developed for detecting whether a call has been answered by an answering machine or a person. For example, US Patent 5,371 ,787 to Hamilton uses a combination of a click detector, a ring detector, a voice detector, click analyzer, ring analyzer, noise analyzer, answer analyzer, silence analyzer, and voice analyzer to distinguish whether a telephone was answered by an answering machine based on time intervals of voice and silence within the audio signal.
Each of US Patents 5,430,792 to Jesurum et al., US Patent 5,724,420 to Torgrim, and US Patent 5,828,731 to Szlam et al. similarly distinguishes between the existence of voice and silence within the audio signal to determine whether the telephone has been answered by an answering machine.
In a separate field of technology, traditional ring back (e.g. a cadence of 2 seconds on, 4 seconds off in the US) is being replaced by customized ring back audio content. For example, the audio content can be any recorded audio such as a spoken message, music, a performed audio monolog (such as comedy), or other recorded audible sound.
A problem exists in that the known technology for distinguishing between whether a telephone has been answered by a machine or a person uses detecting the presence of (or detecting of the discontinuity of) transitions in the audio signal between: i) "ring" and "silence" in traditional ring back cadence, ii) clicks, iii) voice, and iv) silence to both distinguish when a telephone is answered and whether the telephone was answered by a person or a machine.
Replacing the traditional ring back cadence with audio content eliminates an easily detectible sequence of events within the audio signal (the transitions between ring and silence) that is used by traditional systems to: i) detect answering of the telephone; and ii) initiate the measurement of time elapsing between the audio discontinuities of voice and silence used as input for the algorithms for determining whether the call was answered by a person or an answering machine.
In one aspect of the present invention, what is needed is a system and method for distinguishing audio signals received in response to placing an outbound call and, more particularly, to an automated system and method for analyzing audio content (as opposed to discontinuities in the audio signal) and taking one of a plurality of actions based on a characteristic or set of characteristics of the audio signal. In another aspect of the present invention, what is needed is a system and method for detecting when an outbound telephone call has been answered in response to placing an outbound call that does not rely on detecting traditional ring back cadence.
In yet another aspect of the present invention, what is needed is a system and method for detecting whether an outbound telephone call has been answered in a network lacking traditional ring back cadence and, if answered,
whether such outbound call has been answered by a person or an answering machine.
Disclosure of the Invention A first aspect of the present invention comprises an action direction system for directing action based on distinguishing audio content received in response to placing an outbound call.
The system comprises an audio signal analysis system and an audio content analysis system. The audio signal analysis system directs a portion of an audio signal that comprises audio content to the audio content analysis system.
The audio content analysis system: i) receives portions of the audio signal comprising audio content; and ii) directs handling of the outbound call in response to detecting a characteristic of the audio content. The audio content analysis system: i) directs a first handling of the outbound call in response to identifying a first characteristic of the audio content; and ii) directs a second handling of the outbound call in response to identifying a second characteristic of the audio content.
The first handling of the outbound call may be directed in response to identifying a characteristic of the audio content associated with recorded content and the second handling of the outbound call may be directed in response to identifying a characteristic of the audio content associated with real time spoken audio.
The characteristic of the audio content that is associated with recorded audio content may be a repetitive measure (such as music) or the characteristic of the audio content that is associated with recorded audio may be an extraneous intensity/frequency spectrum pattern (e.g. outside a recognizable voice intensity/frequency spectrum pattern).
A handling system may direct handling of the outbound call in response to a combination of signal direction provided by the audio signal analysis system and a content direction provided by the audio content analysis system. The signal direction provided by the audio signal analyses system may
identify a portion of the audio signal representing audio content and a portion of the audio signal representing events from a group of signal events consisting of: i) binary ring cadence; ii) binary busy cadence; iii) an "off hook" transition click; and iv) audio below a silence threshold. The content direction provided by the audio content analysis identifies a characteristic of the audio content.
The handling system may: i) direct a first handling of the outbound call in response to the content direction identifying a first characteristic of the audio content; and ii) direct a second handling of the outbound call in response to the content direction identifying a second characteristic of the audio content.
More specifically, the handling system may: i) direct handling of the outbound call as unanswered in a ring back state in response to identifying a characteristic of the audio content associated with recorded content before the audio signal analysis system identifies a portion of the audio signal consisting of binary ring cadence; ii) direct handling of the outbound call as answered by a messaging machine in response to identifying a characteristic of the audio content associated with recorded content after the audio signal analysis system identifies a portion of the audio signal consisting of binary ring cadence or an "off hook" transition click; and iii) direct handling of the outbound call answered by a person in response to identifying a characteristic of the audio content associated with real time spoken audio.
Again, the characteristic of the audio content that is associated with recorded audio content may be a repetitive measure (such as music) or the characteristic of the audio content that is associated with recorded audio may be an extraneous intensity/frequency spectrum pattern (e.g. outside a recognizable voice intensity/frequency spectrum pattern).
A second aspect of the present invention comprises a system for detecting audio content ring back in response to placing an outbound call. The system comprises an audio signal analysis system and an audio content analysis system.
The audio signal analysis system directs a portion of an audio signal that comprises audio content to an audio content analysis system in response to
detecting such audio content before detecting a portion of an audio signal that comprises binary ring back cadence.
The audio content analysis system: i) receives portions of the audio signal comprising audio content; and ii) identifies the portion of the audio signal comprising audio content as audio content ring back if a characteristic of the audio content is associated with recorded audio content.
Again, the characteristic of the audio content that is associated with recorded audio content may be a repetitive measure (such as music) or the characteristic of the audio content that is associated with recorded audio may be an extraneous intensity/frequency spectrum pattern (e.g. outside a recognizable voice intensity/frequency spectrum pattern).
For a better understanding of the present invention, together with other and further aspects thereof, reference is made to the following description, taken in conjunction with the accompanying drawings. The scope of the present invention is set forth in the appended claims.
Brief Description of the Drawings
Figure 1 is a block diagram representing an exemplary architecture for an action direction system for directing action based on analysis of audio content within an audio signal in accordance with one embodiment of the present invention;
Figure 2 is a table representing exemplary audio content characteristics and associated secondary characteristics in accordance with one embodiment of the present invention; Figure 3 is a table representing exemplary event parameters in the context of placing an outbound call and a direction output associated therewith in accordance with one embodiment of the present invention; and
Figure 4 is a block diagram representing exemplary implementation of a system for direction action based on analysis of audio content in an automated dialing system.
Detailed Description of the Exemplary Embodiments
The present invention will now be described in detail with reference to the drawings. In the drawings, each element with a reference number is similar to other elements with the same reference number independent of any letter designation following the reference number. In the text, a reference number with a specific letter designation following the reference number refers to the specific element with the number and letter designation and a reference number without a specific letter designation refers to all elements, with the same reference number independent of any letter designation following the reference number in the drawings.
It should also be appreciated that many of the elements discussed in this specification may be implemented in a hardware circuit(s), a processor executing software code, or a combination of a hardware circuit(s) and a processor or control block of an integrated circuit executing machine readable code. As such, the term circuit, module, server, or other equivalent description of an element as used throughout this specification is intended to encompass a hardware circuit (whether discrete elements or an integrated circuit block), a processor or control block executing code, or a combination of a hardware circuit(s) and a processor and/or control block executing code. Figure 1 represents an overview of an action direction system 10 for directing action based on analyzing an audio content portion of an audio signal 14 (e.g audio content 15) received in response to placing an outbound call. The action direction system 10 receives an audio signal 14 from the telephony network 12 in response to placement of an outbound call - typically placed by an automated dialing system.
The action direction system 10 may comprise an audio signal analysis system 16, an audio content analysis system 20, and a handling system 26. It should be appreciated that the grouping of functions performed by each of the audio signal analysis system 16, the audio content analysis system 20, and the handling system 26 is for purposes of facilitating teaching of the present invention herein and those skilled in the art will recognize that in any embedded system the grouping of functions is a matter of design choice.
In general, the audio signal analysis system 16 uses known systems to analyze the audio signal 14 to distinguish between portions of the audio signal 14 which represent i) in-band signaling such as binary ring cadence and binary busy cadence; ii) an off-hook transition click; iii) audio below a silence threshold; and iv) audio content.
Audio content 15 comprises a portion of the audio signal 14, other than in-band signaling, with a varying intensity and frequency above a silence threshold which, when converted to acoustic sound, has significance to a person, typically linguistic significance (such as spoken words) or musical significance (such as sung words and/or musical instruments).
A signal direction 22 provides a signal direction to the handling system 26 identifying each such portion of the audio signal 14 and may provide an audio content direction 18 to the audio content analysis system 20 identifying the portion(s) of the audio signal 14 representing audio content 15. Alternatively, in an implementation of the present invention wherein the audio signal 14 is not directly available to the audio content analysis system 20, the audio content direction 18 (identifying of the portion(s) of the audio signal representing audio content) may itself contain the audio content 15 or the portion of the audio signal 14 representing the audio content 15. The audio content analysis system 20 receives the portions of the audio signal 14 comprising audio content 15 and directs handling of the outbound call by detecting a characteristic of the audio content 15 and providing a content direction 24 identifying the characteristic (or associated characteristic) of the audio content 15 to the handling system 26. The audio content analysis system 20 may comprise known digital signal processing systems, narrow band filters, and pattern matching algorithms for identifying and distinguishing between characteristics of the audio content.
For example, turning to the table of Figure 2, various characteristics 42 and their associated characteristic 44 are shown. One example of a characteristic 42 includes repetitive measure (characteristic 42a) such as musical rhythm or beat detected within the intensity pattern and frequency spectrum (e.g. the intensity/frequency spectrum) of the portion of the audio
signal 14 representing audio content 15. The associated characteristic 44 associated with a repetitive measure 42a is recorded content 44a because, within the context of answering a telephone call, music is typically modulated onto the phone line audio signal 14 by a machine that plays a recording such as an answering machine, voice mail, or a ring back content server. Music is rarely performed live at the answering of a telephone.
Another example of a characteristic 42 includes an extraneous intensity/frequency spectrum (characteristic 42b). Human speech typically has a recognizable intensity and frequency spectrum (e.g. S. S. I. F. S or speech shaped intensity/frequency spectrums). Audio content with an intensity and/or frequency spectrum that is outside of the speech shaped intensity/frequency spectrum and above a hiss threshold is, for purposes of this application, referred to as an extraneous intensity/frequency spectrum pattern. The associated characteristic 44 associated with an extraneous intensity/frequency spectrum 42b is recorded content 44a because, within the context of answering a telephone call, audio content other than audio content dominated by human speech is typically modulated onto the phone line by a machine that plays a recording such as an answering machine, voice mail, or a ring back content server. One example of extraneous intensity/frequency may include laughter or applause within a recording of a spoken performance such as that of a comedian.
Another example of a characteristic 42 includes a speech shaped intensity/frequency spectrum - lasting for an extended duration (on the order of two seconds or more) from its start (e.g. a continuous speech shaped intensity/frequency spectrum 42c of an extended duration). The associated characteristic 44 associated with continuous speech shaped intensity/frequency spectrum 42c of an extended duration is recorded content 44a because in the context of answering a telephone, human speech that continues without a pause for a return greeting of 350ms to 2,000 ms is typically associated with a pre-recorded announcement rather than a human making a greeting and pausing for a return greeting (e.g. a return greeting pause).
Another example of a characteristic 42 includes a speech shaped
intensity/frequency spectrum - with a repetitive pattern (e.g. a repetitive speech shaped intensity/frequency spectrum 42d). The associated characteristic 44 associated with repetitive speech shaped intensity/frequency spectrum 42d is real time spoken audio 44b because, within the context of answering a telephone, human speech that repeats one or more words (with a return greeting pause there between) is a characteristic of a human speaking a greeting, expecting a response, and repeating the greeting if no response is forth coming.
Another example of a characteristic 42 includes a discontinuity 42e in the intensity/frequency spectrum. The associated characteristic 44 associated with discontinuity 42e in the intensity/frequency spectrum is an answer event 44c because, within the context of answering a telephone, a discontinuity 42e is a characteristic of the change in audio content associated with a human "taking over" from machine generated audio content such as when a person answers the telephone in the middle of an answering machine greeting or answers the telephone in the middle of audio content ring back.
Returning to Figure 1 , the handling system 26 receives the signal direction 22 from the audio signal analysis system 16 and receives the content direction 24 from the audio content analysis system 20 and directs handling of the outbound call in response thereto by generating a direction output 28.
Turning to Figure 3, a table representing exemplary handling in response to an event parameter 46 (e.g. various permutations of the signal direction 22 and the content direction 24) is shown.
In one example of an event parameter 46a, the presence of binary busy cadence within the audio signal 14 is associated with direction output 28a to handle the present status of the outbound call as unanswered and busy.
In another example of an event parameter 46b, the presence of audio content 15 within the audio signal 14 with a characteristic 42 associated with recorded content 44a (both of Figure 2) before the existence of binary ring back cadence within the audio signal 14 can be interpreted as audio content ring back and the direction output 28b is a direction to maintain a ring back state (e.g. handle the present status of the outbound call as in a ring back state).
In another example of an event parameter 46c, the presence of binary ring back cadence within the audio signal 14 followed by audio content 15 ' within the audio signal 14 with a characteristic 42 associated with recorded content 44a (both of Figure 2) can be interpreted as recorded audio content from an answering machine or voice mail server and the direction output 28c is a direction to handle the present status of the outbound call as answered by a machine.
In another example of an event parameter 46d, the presence of an off- hook transition click within the audio signal 14 followed by audio content 15 within the audio signal 14 with a characteristic 42 associated with recorded content 44a (both of Figure 2) can be interpreted as recorded audio content from an answering machine or voice mail and the direction output 28c is a direction to handle the present status of the outbound call as answered by a machine. In another example of an event parameter 46e, the presence of audio content 15 within the audio signal 14 with a characteristic 42 associated with real time spoken audio 44b (both of Figure 2) can be interpreted as human speech and the direction output 28d is a direction to handle the present status of the outbound call as answered by a person. In another example of an event parameter 46f, the presence of audio content 15 within the audio signal 14 (which may be ambiguous as to whether recorded content of real time spoken audio), followed by audio below a silence threshold lasting between 350 ms and 2,000ms, followed by audio content 15 (again, which may be ambiguous as to whether recorded content of real time spoken audio) which, in the aggregate represents a repetitive speech shaped intensity/frequency spectrum (42d of Figure 2) can be interpreted as human speech and the direction output 28d is a direction to handle the present status of the outbound all as answered by a person.
The block diagram of Figure 4 represents an exemplary implementation of the action direction system 10 within an automated dialing system 30. The automated dialing system 30 couples to the telephone network 12 for placing outbound calls. The automated dialing system 30 may also be coupled to any
of an interactive voice response (IVR) system 48, a recorded message system 50, and a local telephone network 32 for handling of the outbound calls once answered. In this example, an outbound call, after being answered, may be coupled to the IVR system 42 for automated interaction with the called party, coupled to the recorded message system 44 for playing a message to the called party, or coupled to a service representative 34 over the local telephone network 32 for service representative interaction with the called party.
The automated dialing system 30 comprises an outbound call placement system 36 and the action direction system 10. The outbound call placement system 36 comprises an automated handling system 40 and a service representative connection system 38. Upon placing an outbound call in accordance with traditional automated dialing technology, the audio signal is coupled to the action direction system 10 which, in turn, provides a direction output signal 28 to the automated handling system 40. If and when the direction output signal 28 indicates that the outbound call is in an answered by a person state: i) the automated handling system 40 may couple the outbound call to the IVR system 48 or the recorded message system 50; or ii) the service representative connection system 38 may couple the outbound call to a service representative 34. In summary, systems and methods of the present invention provide for: i) distinguishing audio received in response to placing an outbound call by analyzing audio content within an audio signal (as opposed to detecting discontinuities in the audio signal) and taking one of a plurality of actions based on a characteristic of the audio signal; ii) detecting when an outbound telephone call has been answered in response to placing an outbound call that does not rely on detecting traditional ring back cadence; iii) detecting whether an outbound telephone call has been answered in a network lacking traditional ring back cadence; and iv) if answered, whether such outbound call has been answered by a person or an answering machine. Although the invention has been shown and described with respect to certain exemplary embodiments, it is obvious that equivalents and modifications will occur to others skilled in the art upon the reading and
understanding of the specification. The present invention includes all such equivalents and modifications, and is limited only by the scope of the following claims.
Claims
1. An action direction system for directing action based on distinguishing audio content received in response to placing an outbound call, the action direction system comprising: an audio signal analysis system directing a portion of an audio signal that comprises audio content to an audio content analysis system; and the audio content analysis system: receiving portions of the audio signal comprising audio content; and directing handling of the outbound call in response to detecting a characteristic of the audio content.
2. The system of claim 1 , wherein the audio content analysis system: directs a first handling of the outbound call in response to identifying a first characteristic of the audio content; and directs a second handling of the outbound call in response to identifying a second characteristic of the audio content.
3. The system of claim 2, wherein: the first handling of the outbound call is directed in response to identifying a characteristic of the audio content associated with recorded content; the second handling of the outbound call is directed in response to identifying a characteristic of the audio content associated with real time spoken audio. '
4. The system of claim 3, wherein the characteristic of the audio content that is associated with recorded audio content is a repetitive measure.
5. The system of claim 3, wherein the characteristic of the audio content that is associated with recorded audio is an extraneous intensity/frequency spectrum pattern.
6. The system of claim 1 , further comprising a handling action system directing handling of the outbound call in response to a combination of: a signal direction provided by the audio signal analyses system, the signal direction identifying a portion of the audio signal representing one of a plurality of audio events from a group of audio events consisting of: i) binary ring cadence; ii) binary busy cadence; iii) an "off hook" transition click; iv) audio below a silence threshold; and v) audio content; and a content direction provided by the audio content analysis system, the content direction identifying a characteristic of the audio content.
7. The system of claim 6, wherein the handling action system: directs a first handling of the outbound call in response to the content direction identifying a first characteristic of the audio content; and directs a second handling of the outbound call in response to the content identify a second characteristic of the audio content.
8. The system of claim 6, wherein the handling action system: directs handling of the outbound call as unanswered in a ring back state in response to identifying a characteristic of the audio content associated with recorded content before the audio signal analysis system identifies a portion of the audio signal consisting of binary ring cadence; directs handling of the outbound call as answered by a messaging machine in response to identifying a characteristic of the audio content associated with recorded content after the audio signal analysis system identifies a portion of the audio signal consisting of one of binary ring cadence and an "off hook" transition click; and directs handling of the outbound call answered by a person in response to identifying a characteristic of the audio content associated with real time spoken audio.
9. The system of claim 8, wherein the characteristic of the audio content that is associated with recorded audio content is a repetitive measure.
10. The system of claim 8, wherein the characteristic of the audio content that is associated with recorded audio is an extraneous intensity/frequency spectrum pattern.
11. A system for detecting audio content ring back in response to placing an outbound, the system comprising: an audio signal analysis system directing the portion of an audio signal that comprises audio content to an audio content analysis system in response to detecting such audio content before detecting a portion of an audio signal that comprises binary ring back cadence; and the audio content analysis system: receiving portions of the audio signal comprising audio content; and identifying the portion of the audio signal comprising audio content as audio content ring back if a characteristic of the audio content is associated with recorded audio content.
12. The system of claim 11 , wherein the characteristic of the audio content that is associated with recorded audio content is a repetitive measure.
13. The system of claim 11 , wherein the characteristic of the audio content that is associated with recorded audio is an extraneous intensity/frequency spectrum pattern.
14. A method for directing handling of an outbound telephone call based on distinguishing audio content received in response to placing an outbound call, the method comprising: identifying a portion of the audio signal representing one of a plurality of audio events from a group of audio events consisting of: i) binary ring cadence; ii) binary busy cadence; iii) an "off hook" transition click; iv) audio below a silence threshold; and v) audio content; directing a portion of an audio signal that comprises audio content to an audio content analysis system; analyzing the audio content and generating a content direction identifying a characteristic of the audio content; directing handling of the outbound call based on a combination of both a sequence of events and the characteristic of the audio content.
15. The method of claim 14, wherein the step of directing handling of the outbound call based on a combination of both a sequence of events and the characteristic of the audio content comprises directing a first handling of the outbound call in response to identifying a first characteristic of the audio content; and directing a second handling of the outbound call in response to identifying a second characteristic of the audio content.
16. The method of claim 15, wherein: the first handling of the outbound call is directed in response to identifying a characteristic of the audio content associated with recorded content; the second handling of the outbound call is directed in response to identifying a characteristic of the audio content associated with real time spoken audio.
17. The method of claim 16, where the characteristic of the audio content that is associated with recorded audio content is a repetitive measure.
18. The method of claim 16, where the characteristic of the audio content that is associated with recorded audio is an extraneous intensity/frequency spectrum pattern.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP06816246A EP1932326A4 (en) | 2005-10-07 | 2006-10-04 | An automated system and method for distinguishing audio signals received in response to placing an outbound call |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/246,409 | 2005-10-07 | ||
US11/246,409 US8150023B2 (en) | 2005-10-07 | 2005-10-07 | Automated system and method for distinguishing audio signals received in response to placing and outbound call |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2007044422A2 true WO2007044422A2 (en) | 2007-04-19 |
WO2007044422A3 WO2007044422A3 (en) | 2007-11-01 |
Family
ID=37943353
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2006/038840 WO2007044422A2 (en) | 2005-10-07 | 2006-10-04 | An automated system and method for distinguishing audio signals received in response to placing an outbound call |
Country Status (3)
Country | Link |
---|---|
US (1) | US8150023B2 (en) |
EP (1) | EP1932326A4 (en) |
WO (1) | WO2007044422A2 (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9386155B2 (en) | 2009-01-28 | 2016-07-05 | Virtual Hold Technology, Llc | Communication device for establishing automated call back using queues |
US8526591B2 (en) | 2010-12-21 | 2013-09-03 | Bandwidth.Com, Inc. | Systems and methods for implementing a hold-call-back feature in a telecommunications network |
US8718272B2 (en) | 2011-03-01 | 2014-05-06 | Verizon Patent And Licensing Inc. | Contact center routing |
US9020131B2 (en) | 2011-03-01 | 2015-04-28 | Verizon Patent And Licensing Inc. | Contact center call back |
WO2012122568A1 (en) * | 2011-03-10 | 2012-09-13 | Ahmed Tewfik Bouzid | Answering machine detection |
CN103295585A (en) * | 2012-02-24 | 2013-09-11 | 北京英立讯科技有限公司 | Processing system and method identifying whether telephone automatic dialing is responded by real human |
US9516168B2 (en) | 2012-10-19 | 2016-12-06 | Virtual Hold Technology, Llc | Managing, directing, and queuing communication events using near-field communications |
EP3114829B1 (en) * | 2014-03-07 | 2020-05-27 | Dialogtech Inc. | Phone fraud deterrence system for use with toll free and other fee generating numbers |
US10477022B2 (en) | 2017-11-22 | 2019-11-12 | Repnow Inc. | Automated telephone host system interaction |
US11120820B2 (en) | 2018-12-05 | 2021-09-14 | International Business Machines Corporation | Detection of signal tone in audio signal |
GB2596821A (en) * | 2020-07-07 | 2022-01-12 | Validsoft Ltd | Computer-generated speech detection |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030083875A1 (en) | 2001-10-23 | 2003-05-01 | Brown Micheal Kenneth | Unified call classifier for processing speech and tones as a single information stream |
US20040002865A1 (en) | 2002-06-28 | 2004-01-01 | Chan Norman C. | Apparatus and method for automatically updating call redirection databases utilizing semantic information |
Family Cites Families (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5134651A (en) * | 1991-04-18 | 1992-07-28 | Codecom Rural Communications, Inc. | Method and apparatus for providing answer supervision and an autonomous pay telephone incorporating the same |
US5430792A (en) * | 1991-05-03 | 1995-07-04 | Electronic Information Systems, Inc. | Automated telephone calling system |
US5581602A (en) * | 1992-06-19 | 1996-12-03 | Inventions, Inc. | Non-offensive termination of a call detection of an answering machine |
US5371787A (en) * | 1993-03-01 | 1994-12-06 | Dialogic Corporation | Machine answer detection |
US5506898A (en) * | 1994-07-12 | 1996-04-09 | At&T Corp. | Expected wait-time indication arrangement |
JP3308718B2 (en) * | 1994-07-28 | 2002-07-29 | 富士通株式会社 | Automatic transmission control method and apparatus |
US5828781A (en) * | 1994-08-11 | 1998-10-27 | Toyo Ink Manufacturing Co., Ltd. | Color image reproducing system with image signal correction function |
GB2293723B (en) * | 1994-09-28 | 1999-04-14 | Rockwell International Corp | Automatic call distributor with answer machine detection apparatus and method |
US5627884A (en) * | 1995-06-26 | 1997-05-06 | Williams; Mark J. | Method for returning inbound calls |
US5644625A (en) * | 1995-09-01 | 1997-07-01 | Faxts-Now, Inc. | Automatic routing and rerouting of messages to telephones and fax machines including receipt of intercept voice messages |
US5796791A (en) * | 1996-10-15 | 1998-08-18 | Intervoice Limited Partnership | Network based predictive dialing |
US6058180A (en) * | 1997-03-17 | 2000-05-02 | Eagletech Communications, Inc., | Automatic person-following communication system |
US6041116A (en) * | 1997-05-05 | 2000-03-21 | Aspect Telecommunications Corporation | Method and apparatus for controlling outbound calls |
US6400808B1 (en) * | 1997-11-26 | 2002-06-04 | At&T Corp | System and method for providing call subject information to a called party |
US6563921B1 (en) * | 1997-12-31 | 2003-05-13 | Virtual Hold Technology, Llc | Automatic call director first in first out accessory |
US6754334B2 (en) * | 1997-12-31 | 2004-06-22 | Virtual Hold Technology, Llc | Automatic call director first in first out accessory |
US6278777B1 (en) * | 1998-03-12 | 2001-08-21 | Ser Solutions, Inc. | System for managing agent assignments background of the invention |
US6754332B1 (en) * | 1998-11-02 | 2004-06-22 | Concerto Software, Inc. | Object oriented system and method for directing incoming telephone calls |
US6208970B1 (en) * | 1998-12-21 | 2001-03-27 | Nortel Networks Limited | Method and system for estimation of a source of a voice signal |
US6985559B2 (en) * | 1998-12-24 | 2006-01-10 | Mci, Inc. | Method and apparatus for estimating quality in a telephonic voice connection |
US6584191B1 (en) * | 1999-08-27 | 2003-06-24 | Aspect Communications Corporation | Staffing-based percentage-allocation routing using real-time data |
US6546097B1 (en) * | 1999-05-13 | 2003-04-08 | Rockwell Electronic Commerce Corp. | Automatic call distribution system with signal generator and method |
US6694009B1 (en) * | 1999-06-15 | 2004-02-17 | Avaya Technology Corp. | Estimation of a work item's wait-time from the present stages of processing of preceding work items |
US6731725B1 (en) * | 1999-06-28 | 2004-05-04 | Keith A. Merwin | Computerized system for the receipt, recordation, scheduling and redelivery of telephone messages |
US6549621B1 (en) * | 1999-07-26 | 2003-04-15 | Nortel Networks Limited | Method and system for integrating a computer and a telephone |
US6999565B1 (en) * | 2000-02-01 | 2006-02-14 | Envoyworldwide, Inc. | Multi-mode message routing and management |
CA2420679C (en) * | 2000-09-01 | 2010-11-09 | Eliza Corporation | Speech recognition method and system to determine the status of an outbound telephone call |
US6744881B1 (en) * | 2000-09-06 | 2004-06-01 | Convergys Customer Management Group, Inc. | System and method for automated customer calling |
US7929562B2 (en) | 2000-11-08 | 2011-04-19 | Genesis Telecommunications Laboratories, Inc. | Method and apparatus for optimizing response time to events in queue |
US6728363B2 (en) * | 2000-12-29 | 2004-04-27 | Nortel Networks Limited | Determining expected call waiting time in a call center queue |
US6829331B2 (en) * | 2001-01-02 | 2004-12-07 | Soundbite Communications, Inc. | Address book for a voice message delivery method and system |
US6766013B2 (en) * | 2001-06-05 | 2004-07-20 | Avaya Technology Corp. | Timely shut-down of a real-time work center |
US7006608B2 (en) * | 2001-06-28 | 2006-02-28 | Karl Seelig | Software algorithm and method enabling message presentation during a telephone ringing signal period |
WO2003028356A1 (en) * | 2001-09-26 | 2003-04-03 | Hrj Development Corporation | Predictive dialing system and method |
US7043006B1 (en) * | 2002-02-13 | 2006-05-09 | Aastra Intecom Inc. | Distributed call progress tone detection system and method of operation thereof |
US6850602B1 (en) * | 2002-03-27 | 2005-02-01 | Avaya Technology Corp. | Method and apparatus for answering machine detection in automatic dialing |
US6748060B2 (en) * | 2002-04-08 | 2004-06-08 | Plantronics, Inc. | Apparatus and method for providing voice telephone instructions |
US7174011B2 (en) * | 2003-07-11 | 2007-02-06 | At & T Knowledge Ventures Lp | Telephone call center with method for providing customer with wait time updates |
US7171245B2 (en) * | 2004-05-06 | 2007-01-30 | Chunghwa Telecom Co., Ltd. | Method for eliminating musical tone from becoming wind shear sound |
US8781092B2 (en) * | 2005-05-16 | 2014-07-15 | Noble Systems Corporation | Systems and methods for callback processing |
-
2005
- 2005-10-07 US US11/246,409 patent/US8150023B2/en active Active
-
2006
- 2006-10-04 EP EP06816246A patent/EP1932326A4/en not_active Ceased
- 2006-10-04 WO PCT/US2006/038840 patent/WO2007044422A2/en active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030083875A1 (en) | 2001-10-23 | 2003-05-01 | Brown Micheal Kenneth | Unified call classifier for processing speech and tones as a single information stream |
US20040002865A1 (en) | 2002-06-28 | 2004-01-01 | Chan Norman C. | Apparatus and method for automatically updating call redirection databases utilizing semantic information |
Non-Patent Citations (1)
Title |
---|
See also references of EP1932326A4 |
Also Published As
Publication number | Publication date |
---|---|
EP1932326A2 (en) | 2008-06-18 |
EP1932326A4 (en) | 2009-05-13 |
US20070116208A1 (en) | 2007-05-24 |
US8150023B2 (en) | 2012-04-03 |
WO2007044422A3 (en) | 2007-11-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8150023B2 (en) | Automated system and method for distinguishing audio signals received in response to placing and outbound call | |
US10110741B1 (en) | Determining and denying call completion based on detection of robocall or telemarketing call | |
US10320982B2 (en) | Speech recognition method of and system for determining the status of an answered telephone during the course of an outbound telephone call | |
US6850602B1 (en) | Method and apparatus for answering machine detection in automatic dialing | |
US7310412B1 (en) | Personalized recorded message via message delivery system | |
US6208970B1 (en) | Method and system for estimation of a source of a voice signal | |
US8515026B2 (en) | Voice response apparatus and method of providing automated voice responses with silent prompting | |
US10277740B2 (en) | Live person detection in an automated calling system | |
US8660248B2 (en) | Method and structure for controlling incoming communication notification | |
US9583108B2 (en) | Voice detection for automated communication system | |
US20050276390A1 (en) | Method and system for identifying a party answering a telephone call based on simultaneous activity | |
WO2004093411A2 (en) | System and method for call and answer determination for automated calling systems | |
US9679584B1 (en) | Method of matching a digitized stream of audio signals to a known audio recording | |
EP0941597B1 (en) | Interactive apparatus and method | |
US6912271B1 (en) | Personalized recorded message via message delivery system | |
US20130151248A1 (en) | Apparatus, System, and Method For Distinguishing Voice in a Communication Stream | |
US6724865B1 (en) | Arrangement for measuring response times in a voice response system using a bulk call generator | |
EP1830547A1 (en) | A device for detecting ring back tone and a method thereof | |
GB2596821A (en) | Computer-generated speech detection | |
CA2712853C (en) | Speech recognition method and system to determine the status of an outbound telephone call | |
JPS63299446A (en) | Mechanical input system by sound of voice or the like | |
Holdsworth | Voice processing | |
US20090103699A1 (en) | Methods and systems for determining customer hang-up during a telephonic communication between a customer and a contact center | |
WO2014152542A2 (en) | Voice detection for automated communication system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2006816246 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |