Dynamic voice response control based on a weighted pace of spoken terms

• US 9,443,514 B1
• Filed: 02/08/2012
• Issued: 09/13/2016
• Est. Priority Date: 02/08/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Taubman, Gabriel
• Primary Examiner(s): Kazeminezhad, Farzad
• Application Number:
  US13/368,681
• Time in Patent Office: 1,679 Days
• Field of Search: 704/270, 704/200
• US Class Current: 1/1
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A system is configured to obtain a first voice request, from a client, to access a voice processing system that processes voice communications received from clients; determine a first pace at which terms, associated with the first voice request, are spoken by a user of the client; determine a second pace, associated with the user, based on terms, associated with other voice requests, spoken by the user and users of the clients prior to receiving the first voice request by using a weighted average of the pace associated with the user of the client and a pace associated with the users of the clients other than the client; compare the first pace to the second pace; determine a third pace based on the comparison; and send, to the client, a voice response to be outputted at the third pace.

Claims

1. A method performed by one or more server devices associated with a voice processing system, the method comprising:

obtaining, by at least one of the one or more server devices and from a client device, a first voice request to access the voice processing system that processes voice communications received from client devices;

determining, by at least one of the one or more server devices and based on the first voice request, a first pace at which terms, associated with the first voice request, are spoken by a user of the client device;

determining, by at least one of the one or more server devices, a second pace, where the second pace is based on a weighted average of a user pace of terms spoken, by the user when accessing the voice processing system, prior to the first voice request being received, and another pace of terms spoken by users of other client devices, other than the client device, when accessing the voice processing system, wherein a first weight assigned to the user pace is different than a second weight assigned to the another pace;

comparing, by at least one of the one or more server devices, the first pace to the second pace;

determining, by at least one of the one or more server devices, a third pace based on the comparison of the first pace to the second pace; and

sending, to the client device, a voice response to be outputted at the third pace.

2. The method of claim 1, where the third pace corresponds to:

a faster pace than a medium pace when the first pace is greater than the second pace,

the medium pace when the first pace is approximately equal to the second pace, and

a slower pace than the medium pace when the first pace is less than the second pace, where the faster pace, the medium pace, and the slower pace are different.

3. The method of claim 2, where the faster pace corresponds to a high-level of perceived urgency associated with the user,

where the medium pace corresponds to a medium-level of perceived urgency associated with the user, where the medium-level of perceived urgency is less urgent than the high-level of perceived urgency, and

where the slower pace corresponds to a low-level of perceived urgency associated with the user, where the low-level of perceived urgency is less urgent than the medium-level of perceived urgency.

4. The method of claim 1, where the first voice request includes first video content of the user, and

where the method further includes;

comparing the first video content to second video content, that was received prior to the first video content, where the second video content corresponds to a first level of perceived urgency associated with the user;

identifying a second level of perceived urgency, associated with the user and relative to the first level of perceived urgency, based on the comparison of the first video content to the second video content; and

sending, to the client device, a voice response to be outputted at the third pace based on the first level of perceived urgency and the second level of perceived urgency.

5. The method of claim 1, where determining the first pace further includes:

identifying a quantity of terms within a portion of the first voice request;

identifying a time period associated with the portion; and

identifying the first pace based on the quantity of terms and the identified time period.

6. The method of claim 1, where determining the first pace further includes:

detecting one or more terms associated with the first voice request; and

identifying the first pace based on a respective period of time for the user to speak each of the one or more terms.

7. The method of claim 1, where determining the second pace includes:

detecting a portion of the first voice request spoken by the user;

identifying a time period for at least one of the users, of the other client devices, to speak the detected portion; and

identifying the second pace based on the identified time period for the at least one of the users, of the other client devices, to speak the detected portion.

8. The method of claim 1, where determining the second pace includes:

detecting one or more terms, spoken by the user, during the first voice request;

identifying a respective period of time for the user to speak each of the one or more terms during a second voice request, received prior to receiving the first voice request; and

identifying the second pace based on the respective period of time for the user to speak each of the one or more terms during the second voice request.

9. The method of claim 1, where determining the first pace further includes:

converting the terms, associated with the first voice request, to text at a rate that depends on a pace at which the first voice request is received from the client device; and

identifying the first pace based on the rate at which the terms are converted to text.

10. The method of claim 1, where the another pace is of terms spoken by a set of users of a same language, age group, or gender as the user when accessing the voice processing system.

11. The method of claim 1, where the another pace is of terms spoken by a set of users of a same geographic area as the user when accessing the voice processing system.

12. A system, comprising:

one or more server devices to;

obtain, from a client device, a first voice request to access a voice processing system that processes voice communications received from client devices,

determine, based on the first voice request, a first pace at which terms, associated with the first voice request, are spoken by a user of the client device,

determine a second pace, where the second pace is based on a weighted average of a user pace of terms spoken, by the user when accessing the voice processing system, prior to the first voice request being received, and another pace of terms spoken by users of other client devices, other than the client device, when accessing the voice processing system, wherein a first weight assigned to the user pace is different than a second weight assigned to the another pace;

compare the first pace to the second pace,

determine a third pace based on the comparison of the first pace to the second pace, and

send, to the client device, a voice response to be outputted at the third pace.

13. The system of claim 12, where the third pace corresponds to:

a faster pace than a medium pace when the first pace is greater than the second pace,

the medium pace when the first pace is approximately equal to the second pace, and

a slower pace than the medium pace when the first pace is less than the second pace, where the faster pace, the medium pace, and the slower pace are different.

14. The system of claim 13, where the faster pace corresponds to a high-level of perceived urgency associated with the user,

where the medium pace corresponds to a medium-level of perceived urgency associated with the user, where the medium-level of perceived urgency is less urgent than the high-level of perceived urgency, and

where the slower pace corresponds to a low-level of perceived urgency associated with the user, where the low-level of perceived urgency is less urgent than the medium-level of perceived urgency.

15. The system of claim 12, where the first voice request includes first video content of the user, and

where the one or more server devices are further to:

compare the first video content to second video content, that was received prior to the first video content, where the second video content corresponds to a first level of perceived urgency associated with the user,

identify a second level of perceived urgency, associated with the user and relative to the first level of perceived urgency, based on the comparison of the first video content to the second video content, and

send, to the client device, a voice response to be outputted at the third pace based on the first level of perceived urgency and the second level of perceived urgency.

16. The system of claim 12, where, when determining the first pace, the one or more server devices are to:

identify a quantity of terms within a portion of the first voice request,

identify a time period associated with the portion, and

identify the first pace based on the quantity of terms and the identified time period.

17. The system of claim 12, where, when determining the first pace, the one or more server devices are to:

detect one or more terms associated with the first voice request, and

identify the first pace based on a respective period of time for the user to speak each of the one or more terms.

18. The system of claim 12, where, when determining the second pace, the one or more server devices are to:

detect a portion of the first voice request spoken by the user,

identify a time period for at least one of the users, of the other client devices, to speak the detected portion, and

identify the second pace based on the identified time period for the at least one of the users, of the other client devices, to speak the detected portion.

19. The system of claim 12, where, when determining the second pace, the one or more server devices are to:

detect one or more terms, spoken by the user, during the first voice request;

identify a respective period of time for the user to speak each of the one or more terms during a second voice request, received prior to receiving the first voice request, and

identify the second pace based on the respective period of time for the user to speak each of the one or more terms during the second voice request.

20. The system of claim 12, where, when determining the first pace, the one or more server devices are to:

convert the terms, associated with the first voice request, to text at a rate that depends on a pace at which the first voice request is received from the client device, and

identify the first pace based on the rate at which the terms are converted to text.

21. A non-transitory computer-readable medium, comprising:

a plurality of instructions which, when executed by one or more processors, cause the one or more processors to;

obtain, from a client device, a first voice request to access a voice processing system that processes voice communications received from client devices;

determine, based on the first voice request, a first pace at which terms, associated with the first voice request, are spoken by a user of the client device;

determine a second pace, where the second pace is based on a weighted average of a user pace of terms spoken, by the user when accessing the voice processing system, prior to the first voice request being received, and another pace of terms spoken by users of other client devices, other than the client device, when accessing the voice processing system, wherein a first weight assigned to the user pace is different than a second weight assigned to the another pace;

compare the first pace to the second pace;

determine a third pace based on the comparison of the first pace to the second pace; and

send, to the client device, a voice response to be outputted at the third pace.

22. The non-transitory computer-readable medium of claim 21, where the third pace corresponds to at least one of:

a faster pace than a medium pace when the first pace is greater than the second pace,

the medium pace when the first pace is approximately equal to the second pace, and

a slower pace than the medium pace when the first pace is less than the second pace, where the faster pace, the medium pace, and the slower pace are different.

23. The non-transitory computer-readable medium of claim 22, where the faster pace corresponds to a high-level of perceived urgency associated with the user,

where the medium pace corresponds to a medium-level of perceived urgency associated with the user, where the medium-level of perceived urgency is less urgent than the high-level of perceived urgency, and

where the slower pace corresponds to a low-level of perceived urgency associated with the user, where the low-level of perceived urgency is less urgent than the medium-level of perceived urgency.

24. The non-transitory computer-readable medium of claim 21, where the first voice request includes first video content of the user, and

where the plurality of instructions which, when executed by the one or more processors, further cause the one or more processors to:

compare the first video content to second video content, that was received prior to the first video content, where the second video content corresponds to a first level of perceived urgency associated with the user;

identify a second level of perceived urgency, associated with the user and relative to the first level of perceived urgency, based on the comparison of the first video content to the second video content; and

send, to the client device, a voice response to be outputted at the third pace based on the first level of perceived urgency and the second level of perceived urgency.

25. The non-transitory computer-readable medium of claim 21, where the one or more instructions, of the plurality of instructions, to determine the first pace, cause the one or more processors to:

identify a quantity of terms within a portion of the first voice request;

identify a time period associated with the portion; and

identify the first pace based on the quantity of terms and the identified time period.

26. The non-transitory computer-readable medium of claim 21, where the one or more instructions, of the plurality of instructions, to determine the first pace, cause the one or more processors to:

detect one or more terms associated with the first voice request; and

identify the first pace based on a respective period of time for the user to speak each of the one or more terms.

27. The non-transitory computer-readable medium of claim 21, where the one or more instructions, of the plurality of instructions, to determine the second pace, cause the one or more processors to:

detect a portion of the first voice request spoken by the user;

identify a time period for at least one of the users, of the other client devices, to speak the detected portion; and

identify the second pace based on the identified time period for the at least one of the users, of the other client devices, to speak the detected portion.

28. The non-transitory computer-readable medium of claim 21, where the one or more instructions, of the plurality of instructions, to determine the second pace, cause the one or more processors to:

detect one or more terms, spoken by the user, during the first voice request;

identify a respective period of time for the user to speak each of the one or more terms during a second voice request, received prior to receiving the first voice request; and

identify the second pace based on the respective period of time for the user to speak each of the one or more terms during the second voice request.

29. The non-transitory computer-readable medium of claim 21, where the one or more instructions, of the plurality of instructions, to determine the first pace, cause the one or more processors to:

convert the terms, associated with the first voice request, to text at a rate that depends on a pace at which the first voice request is received from the client device; and

identify the first pace based on the rate at which the terms are converted to text.