Telephone call handling center where operators utilize synthesized voices generated or modified to exhibit or omit prescribed speech characteristics

• US 20040215451A1
• Filed: 04/25/2003
• Published: 10/28/2004
• Est. Priority Date: 04/25/2003
• Status: Active Grant

• Current Assignee: Dynamic Voice LLC
• Original Assignee: Bvoice Corporation
• Inventors: Macleod, John B.
• Granted Patent: US 7,275,032 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 2021/0135 Voice conversion or morphing
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence
• CPC Class Codes: H04M 2203/252 where a voice mode is enhanced with visual information
• CPC Class Codes: H04M 2203/306 Prerecordings to be used during a voice call
• CPC Class Codes: H04M 2203/357 Autocues for dialog assistance
• CPC Class Codes: H04M 3/527 Centralised call answering arrangements not requiring operator intervention

Abstract

A human operator'"'"'s voice is artificially varied prior to transmission to a remote caller. In one example, the operator indicates target speech content (e.g., actual speech, pre-prepared text, manually entered text) to a speech processing facility, which enunciates the target speech content with an output voice that exhibits prescribed speech characteristics (e.g., accent, dialect, speed, vocabulary, word choice, male/female, timbre, speaker age, fictional character, speech particular to people of a particular geographic region or socioeconomic status or other grouping). Another example is an automated call processing system, where an output voice is selected for each incoming call and information is interactively presented to callers using the output voice selected for their respective calls. In another example, a speech processing facility intercepts the operator'"'"'s speech, manipulates the waveform representing the operator'"'"'s intercepted speech to add or remove prescribed characteristics, and transmits an enunciated output of the manipulated waveform to the caller.

Claims

1. A method for conducting voice communications, comprising operations of:

a human operator receiving telephone calls from a variety of remote callers over time;

for each particular call from a caller, performing operations comprising;

selecting an output voice that exhibits prescribed speech characteristics appropriate to that particular call;

the human operator listening to voice utterances of the caller;

instead of the operator speaking to the caller, performing operations comprising;

the operator selecting target speech content to be conveyed to the caller;

the operator directing a representation of the selected target speech content to a speech processing facility;

the speech processing facility producing a signal representing an enunciation of the target speech content utilizing the selected output voice;

transmitting the signal to the caller.

2. The method of claim 1, where the act of receiving telephone calls comprises one or more of the following:

receiving a voice-over-IP calls, receiving voice wireless communications, receiving calls from landline telephones, receiving satellite telephone calls, receiving voice signals via dedicated data communications circuit, receiving voice signals via shared data communications circuit.

3. The method of claim 1, the operation of selecting an output voice comprises selecting an output voice with prescribed speech characteristics particular to people of one of the following groups:

a geographic region, another specified group.

4. The method of claim 1, where the operation of selecting an output voice comprises selecting an output voice with prescribed speech characteristics that include one or more of the following:

accent, dialect, vocabulary, word choice, speech rate, pitch, tone, timbre, gender, language.

5. The method of claim 1, where the operation of selecting an output voice comprises selecting an output voice with prescribed speech characteristics of a specified fictional character.

6. The method of claim 1, where:

the directing operation comprises the operator speaking the target speech content to the speech processing facility;

the producing operation comprises performing speech recognition upon the target speech content spoken by the operator in order to yield a speech-to-text output, and applying a speech synthesis process to enunciate the speech-to-text output utilizing the selected output voice.

7. The method of claim 1, where:

the directing operation comprises the human operator performing at least one of the following;

designating pre-prepared text from a display palette, designating text via manual character entry;

the producing operation comprises applying a speech synthesis process to the designated text.

8. The method of claim 1, where the operation of selecting the output voice comprises:

identifying a target geographical region by indexing at least one of the following in a pre-prepared database;

(1) an originating telephone number of the caller, (2) identity of the caller, (3) a telephone number dialed by the caller, (4) a billing account associated with the caller, (5) information submitted by the caller during the call;

choosing an output voice having speech characteristics of speakers from the target geographical region.

9. The method of claim 1, the operations of selecting the output voice comprising:

selecting an output voice exhibiting prescribed characteristics of speech appropriate to one or more of the following features of the human operator;

gender of the operator, level of supervisory authority of the operator, another feature associated with the operator.

10. The method of claim 1, further comprising operations of:

the human operator reconfiguring the call so that the operator speaks to the caller in the operator'"'"'s own voice.

11. The method of claim 1, the producing operation comprising:

searching a database for a pre-recorded vocalization of the target speech content utilizing the selected output voice;

replaying pre-recorded vocalizations of any target speech content found in the database, and synthesizing vocalizations of target speech absent from the database.

12. The method of claim 1, where:

the direction operation comprises the operator speaking the target speech content to the speech processing facility;

the producing operation comprises the speech processing facility manipulating a waveform representing the operator'"'"'s speech to change features of the waveform that correspond to prescribed characteristics of the operator'"'"'s speech.

13. A signal-bearing medium tangibly embodying a program of machine-readable instructions executable by a digital processing apparatus to perform operations for conducting a call between an operator and a remote caller, the operations comprising:

receiving designation of an output voice that exhibits prescribed speech characteristics;

receiving from the operator a representation of target speech content to be conveyed to the caller;

producing a signal representing an enunciation of the target speech content utilizing the selected output voice for transmission to the caller instead of the operator'"'"'s own voice.

14. The medium of claim 13, where the producing operation is conducted such that the output voice exhibits prescribed speech characteristics particular to people of one of the following groups:

a geographic region, another specified group.

15. The medium of claim 13, where the producing operation is conducted such that the output voice exhibits prescribed speech characteristics that include one or more of the following:

accent, dialect, vocabulary, word choice, speech rate, pitch, tone, timbre, gender, language.

16. The medium of claim 13, where the producing operation is conducted such that the output voice exhibits prescribed speech characteristics of a specified fictional character.

17. The medium of claim 13, where:

the operation of receiving the representation of target speech content comprises receiving a signal representing the operator speaking the target speech content;

the producing operation comprises performing speech recognition upon the signal in order to yield a speech-to-text output, and applying a speech synthesis process to enunciate the speech-to-text output utilizing the selected output voice.

18. The medium of claim 13, where:

the operation of receiving the representation of target speech content comprises at least one of the following;

receiving pre-prepared text selected from a display palette, receiving text selected via manual character entry;

the producing operation comprises applying a speech synthesis process to the received text.

19. The medium of claim 13, where the operation of receiving designation of an output voice comprises:

receiving designation of an output voice that that exhibits prescribed speech characteristics of speakers from a target geographical region identified by indexing indexing at least one of the following in a pre-prepared database;

(1) an originating telephone number of the caller, (2) identity of the caller, (3) a telephone number dialed by the caller, (4) a billing account associated with the caller, (5) information submitted by the caller during the call.

20. The medium of claim 13, where the operation of receiving designation of an output voice comprises receiving designation of an output voice that exhibits prescribed characteristics of speech appropriate to one or more of the following features of the human operator:

gender of the operator, level of supervisory authority of the operator, another feature associated with the operator.

21. The medium of claim 13, further comprising operations of:

responsive to input from the operator, reconfiguring the call to convey a natural voice of the operator to the caller.

22. The medium of claim 13, the producing operation comprising:

searching a database for a pre-recorded vocalization of the target speech content utilizing the selected output voice;

replaying pre-recorded vocalizations of any target speech content found in the database, and synthesizing vocalizations of target speech absent from the database.

23. The medium of claim 13, where:

the operation of receiving the representation of target speech content comprises receiving a signal representing the operator speaking the target speech content;

the producing operation comprises the speech processing facility manipulating a waveform provided by the signal to change features of the waveform that correspond to prescribed characteristics of the operator'"'"'s speech.

24. Circuitry comprising multiple interconnected electrically conductive elements configured to perform operations for conducting a call between an operator and a remote caller, the operations comprising:

receiving designation of an output voice that exhibits prescribed speech characteristics;

receiving from the operator a representation of target speech content to be conveyed to the caller;

producing a signal representing an enunciation of the target speech content utilizing the selected output voice;

transmitting the signal to the caller instead of the operator'"'"'s own voice.

25. A call processing center for processing telephone calls between an operator and a variety of remote callers over time, comprising:

a call handler configured to select an output voice that exhibits prescribed speech characteristics appropriate to each call;

a user interface configured to convey voice utterances of the caller to an operator and, instead of conveying speech of the operator to the caller, receiving selection by the operator of target speech content to be conveyed to the caller and directing a representation of the selected target speech content to a speech processing facility;

a speech processing facility configured to produce a signal representing an enunciation of the target speech content utilizing the selected output voice for transmission to the caller.

26. A call processing center for processing telephone calls between an operator and a variety of remote callers over time, comprising:

a call handling means for selecting an output voice that exhibits prescribed speech characteristics appropriate to each call;

user interface means for conveying voice utterances of the caller to an operator and, instead of conveying speech of the operator to the caller, receiving selection by the operator of target speech content to be conveyed to the caller and directing a representation of the selected target speech content to a speech processing facility;

speech processing means for producing a signal representing an enunciation of the target speech content utilizing the selected output voice for transmission to the caller.

27. A method for conducting voice communications, comprising operations of:

a human operator listening to voice utterances of a remote caller;

instead of speaking directly to the caller, performing operations comprising;

a speech processing facility intercepting speech of the operator;

the speech processing facility manipulating a waveform representing the operator'"'"'s intercepted speech to change features of the waveform that correspond to prescribed characteristics of the intercepted speech;

transmitting a signal representative of the manipulated waveform to the caller.

28. The method of claim 27, where the prescribed characteristics include at least one of the following:

accent, dialect, speech rate, pitch, tone, timbre, gender.

29. The method of claim 27, where the manipulating operation comprises at least one of the following:

removing certain characteristics of the intercepted speech;

adding certain characteristics to the intercepted speech.

30. A signal bearing medium tangibly embodying a program of machine readable instructions executable by a digital data processing apparatus to perform operations for conducting voice communications between an operator and a remote caller, the operations comprising:

intercepting speech of the operator;

manipulating a waveform representing the operator'"'"'s intercepted speech to change features of the waveform that correspond to prescribed characteristics of the intercepted speech;

transmitting a signal representative of the manipulated waveform to the caller instead of the operator'"'"'s speech.

31. The medium of claim 30, where the prescribed characteristics include at least one of the following:

accent, dialect, speech rate, pitch, tone, timbre, gender.

32. The medium of claim 30, where the manipulating operation comprises at least one of the following:

removing certain characteristics of the intercepted speech;

adding certain characteristics to the intercepted speech.

33. Circuitry comprising multiple interconnected electrically conductive elements configured to perform operations for conducting voice communications between an operator and a remote caller, the operations comprising:

intercepting speech of the operator;

manipulating a waveform representing the operator'"'"'s intercepted speech to change features of the waveform that correspond to prescribed characteristics of the intercepted speech;

transmitting a signal representative of the manipulated waveform to the caller instead of the operator'"'"'s speech.

34. A speech processing facility, comprising:

data storage;

a digital data processor coupled to the storage and programmed to perform operations to produce output speech to a remote caller under direction of an operator, the operations comprising;

receiving input selecting an output voice that exhibits prescribed speech characteristics;

receiving a representation of operator-selected target speech content in at least one of the following forms;

output text selected via manual character entry, pre-prepared output text selected from a display pallet, operator utterance of the target speech content;

producing a signal representing an enunciation of the target speech content utilizing the selected output voice by performing at least one of the following;

(1) applying a speech-to-text process to the operator'"'"'s utterances to yield output text and then applying a text-to-speech process to the output text in order to enunciate speech in the output voice, (2) manipulating a waveform representing the operator'"'"'s utterances to change features of the waveform that correspond to prescribed characteristics of the intercepted speech, (3) applying a text-to-speech process to output text indicated by the operator in order to enunciate speech in the output voice;

transmitting the produced signal to the caller in lieu of the operator'"'"'s own voice.

35. A speech processing facility, comprising:

means for data storage;

digital data processing means for producing output speech to a remote caller under direction of an operator, by;

receiving input selecting an output voice that exhibits prescribed speech characteristics;

receiving a representation of operator-selected target speech content in at least one of the following forms;

output text selected via manual character entry, pre-prepared output text selected by selection from a display pallet, operator utterance of the target speech content;

producing a signal representing an enunciation of the target speech content utilizing the selected output voice by performing at least one of the following;

(1) applying a speech-to-text process to the operator'"'"'s utterances to yield output text and then applying a text-to-speech process to the output text in order to enunciate speech in the output voice, (2) manipulating a waveform representing the operator'"'"'s utterances to change features of the waveform that correspond to prescribed characteristics of the intercepted speech, (3) applying a text-to-speech process to output text indicated by the operator in order to enunciate speech in the output voice;

transmitting the produced signal to the caller in lieu of the operator'"'"'s own voice.

36. A method for operating a call center, comprising:

providing a call processing facility including multiple human telephone operators;

the call processing facility receiving incoming calls and, for at least some calls, referring the calls to human operators;

the operators listening to respective callers and, rather than speaking to the callers, the operators responding with voices electronically conditioned to exhibit prescribed speech characteristics.

37. A call processing method, comprising:

providing an automated call processing system;

the call processing system receiving incoming calls and, for each incoming call from a caller, performing operations comprising;

selecting an output voice by indexing predetermined characteristics associated with the call in a pre-prepared database, and responsive to input from the caller;

interactively outputting information to the caller by enunciating the information utilizing the output voice selected for that caller.

38. The method of claim 37, each output voice exhibiting prescribed characteristics of speech comprising at least one of the following:

accent, dialect, vocabulary, word choice, speech rate, pitch, tone, timbre, gender, language.

39. The method of claim 37, each output voice exhibiting prescribed characteristics of speech particular to people of one of the following groups:

a geographic region, another specified group.

40. The method of claim 37, where the operation of providing an automated call processing system comprises at least one of the following:

providing a voice menu system, providing an interactive information database driven by caller-directed query.

41. The method of claim 37, the operation of interactively outputting information comprises:

outputting information responsive to one or more of the following caller inputs;

DTMF input, voice utterance.

42. The method of claim 37, the enunciating operation comprising at least one of the following:

synthesizing speech;

transmitted pre-recorded speech.

43. An automated call processing system for processing telephone calls received from remote callers, comprising:

a call handler responsive to each incoming call from a caller to select an output voice by indexing predetermined characteristics associated with the call in a pre-prepared database;

a voice menu system, responsive to input from each caller during a call, to interactively output information to that caller by enunciating the information utilizing the output voice selected for that call.

44. The system of claim 43, each output voice exhibiting prescribed characteristics of speech comprising at least one of the following:

accent, dialect, vocabulary, word choice, speech rate, pitch, tone, timbre, gender, language.

45. The system of claim 43, each output voice exhibiting prescribed characteristics of speech particular to people of one of the following groups:

a geographic region, another specified group.

46. The system of claim 43, where voice menu system further comprising an interactive information database driven by caller-directed query.

47. The system of claim 43, the operation of interactively outputting information comprises:

outputting information responsive to one or more of the following caller inputs;

DTMF input, voice utterance.

48. The system of claim 43, the enunciating operation comprising at least one of the following:

synthesizing speech;

transmitted pre-recorded speech.