Voice profile management and speech signal generation

Patent metadata

Field	Value
Publication number	US-9666204-B2
Application number	US-201514700009-A
Country	US
Kind code	B2
Filing date	Apr 29, 2015
Priority date	Apr 30, 2014
Publication date	May 30, 2017
Grant date	May 30, 2017

Abstract

A device includes a receiver, a memory, and a processor. The receiver is configured to receive a remote voice profile. The memory is electrically coupled to the receiver. The memory is configured to store a local voice profile associated with a person. The processor is electrically coupled to the memory and the receiver. The processor is configured to determine that the remote voice profile is associated with the person based on speech content associated with the remote voice profile or an identifier associated with the remote voice profile. The processor is also configured to select the local voice profile for profile management based on the determination.

First claim

What is claimed is:

1. A device comprising:
a receiver configured to receive a remote voice profile;
a memory electrically coupled to the receiver, the memory configured to store a local voice profile associated with a person; and
a processor electrically coupled to the memory and the receiver, the processor configured to:
determine that the remote voice profile is associated with the person based on speech content associated with the remote voice profile or an identifier associated with the remote voice profile;
select the local voice profile for profile management based on the determination that the remote voice profile is associated with the person; and
replace a first segment of the local voice profile with a second segment of the remote voice profile.

2. The device of claim 1 , wherein the local voice profile is associated with a first plurality of substitute speech signals and the remote voice profile is associated with a second plurality of substitute speech signals.

3. The device of claim 2 , wherein the first segment of the local voice profile is replaced with the second segment of the remote voice profile by removing a first substitute speech signal from the first plurality of substitute speech signals and adding a second substitute speech signal of the second plurality of substitute speech signals to the first plurality of substitute speech signals.

4. The device of claim 1 , wherein the receiver includes one or more of an antenna, a network interface, or a combination of the antenna and the network interface.

5. The device of claim 1 , wherein the receiver is configured to receive multiple remote voice profiles associated with multiple persons.

6. The device of claim 1 , further comprising a display configured to present a graphical user interface that includes a representation of the remote voice profile, a representation of the local voice profile, or both.

7. The device of claim 1 , wherein the processor is further configured to:
receive a speech signal from a text-to-speech converter;
detect a use mode of a plurality of use modes, wherein the use mode comprises at least one of a reading mode, a conversation mode, a singing mode, or a command and control mode;
select a demographic domain of a plurality of demographic domains, wherein the demographic domain comprises at least one of a language domain, a gender domain, or an age domain;
select a substitute speech signal of a plurality of substitute speech signals based on the speech signal, the use mode, and the demographic domain, wherein the local voice profile is associated with the plurality of substitute speech signals; and
generate a processed speech signal based on the substitute speech signal.

8. The device of claim 7 , wherein the plurality of substitute speech signals is associated with classifications, wherein each of the classifications has a priority, and wherein the substitute speech signal is selected by comparing a portion of the speech signal to the plurality of substitute speech signals in order of priority.

9. The device of claim 7 , further comprising a microphone configured to receive a training speech signal associated with the person, wherein one or more speech signals of the plurality of substitute speech signals are generated based on the training speech signal.

10. The device of claim 7 , wherein the processor is further configured to:
detect a first use mode of the plurality of use modes associated with a training speech signal; and
associate the first use mode with one or more substitute speech signals of the plurality of substitute speech signals that are generated based on the training speech signal.

11. The device of claim 7 , wherein the processor is further configured to:
detect a first use mode of the plurality of use modes based on a use mode setting when a training speech signal is received; and
associate the first use mode with one or more speech signals of the plurality of substitute speech signals that are generated based on the training speech signal.

12. The device of claim 7 , wherein the processor is further configured to:
associate a singing mode with one or more speech signals of the plurality of substitute speech signals based on determining that a training speech signal corresponds to singing, wherein the one or more speech signals are generated based on the training speech signal;
associate a reading mode with the one or more speech signals based on determining that a reading application was in an activated mode when the training speech signal was received; and
associate a conversation mode with the one or more speech signals based on determining that the training speech signal was captured during a voice call.

13. A method for communication comprising:
receiving a remote voice profile at a device storing a local voice profile, the local voice profile associated with a person;
determining that the remote voice profile is associated with the person based on a comparison of the remote voice profile and the local voice profile, or based on an identifier associated with the remote voice profile;
selecting, at the device, the local voice profile for profile management based on the determination that the remote voice profile is associated with the person; and
replacing a first segment of the local voice profile with a second segment of the remote voice profile.

14. The method of claim 13 , further comprising:
receiving, at the device, an update including data corresponding to a plurality of substitute speech signals associated with the remote voice profile;
associating the plurality of substitute speech signals with the local voice profile;
receiving, at the device, a selection associated with the local voice profile;
receiving, at the device, an input audio signal; and
generating, at the device, a processed speech signal by replacing a portion of the input audio signal with a substitute speech signal of the plurality of substitute speech signals.

15. The method of claim 14 , wherein a first value of a signal to noise ratio associated with the substitute speech signal is greater than a second value of a signal to noise ratio associate with the portion of the input audio signal.

16. The method of claim 14 , further comprising outputting the processed speech signal via a speaker.

17. The method of claim 14 , wherein the selection corresponds to initiation of a voice call from the device to a second device associated with the local voice profile.

18. The method of claim 14 , wherein the selection corresponds to acceptance by the device of a voice call from a second device, and wherein the second device is associated with the local voice profile.

19. The method of claim 14 , further comprising:
comparing, at the device, the portion of the input audio signal to the plurality of substitute speech signals; and
determining, at the device, that the portion of the input audio signal matches the substitute speech signal,
wherein the portion of the input audio signal is replaced with the substitute speech signal based on the determination.

20. The method of claim 14 , wherein the update is received responsive to an update request sent from the device.

21. The method of claim 14 , further comprising:
generating, at the device, a graphical user interface including an option to specify when an update request is to be sent;
providing the graphical user interface to a display device; and
sending the update request based on receiving user input corresponding to the

Assignees

• Qualcomm Inc

Inventors

• Manjunath Sharath
• Sinder Daniel Jared

Classifications

• G10L21/003 Primary

  Changing voice quality, e.g. pitch or formants · CPC title

• G10L17/00

  Speaker identification or verification techniques · CPC title

• G10L21/0208

  Noise filtering · CPC title

• G10L13/033

  Voice editing, e.g. manipulating the voice of the synthesiser · CPC title

• G10L25/48

  specially adapted for particular use · CPC title