System and method of synthetic voice generation and modification
View Patent ↗Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating a synthetic voice. A system configured to practice the method combines a first database of a first text-to-speech voice and a second database of a second text-to-speech voice to generate a combined database, selects from the combined database, based on a policy, voice units of a phonetic category for the synthetic voice to yield selected voice units, and synthesizes speech based on the selected voice units. The system can synthesize speech without parameterizing the first text-to-speech voice and the second text-to-speech voice. A policy can define, for a particular phonetic category, from which text-to-speech voice to select voice units. The combined database can include multiple text-to-speech voices from different speakers. The combined database can include voices of a single speaker speaking in different styles. The combined database can include voices of different languages.
1. A method comprising:
storing, in a database, voice data according to user emotions;
identifying, from user speech, a user emotion;
identifying, via at least one processor and according to the user emotion, a first portion of the voice data, wherein the first portion of the voice data comprises a first emotional content for a first speaker;
identifying, via the at least one processor and according to the user emotion, a second portion of the voice data, wherein the second portion of the voice data comprises a second emotional content for a second speaker; and
synthesizing synthesized speech using the first portion of the voice data and the second portion of the voice data.
2. The method of claim 1 , wherein the first portion of the voice data comprises first text-to-speech voice data and wherein the second portion of the voice data comprises second text-to-speech voice data.
3. The method of claim 1 , wherein the synthesized speech corresponds to the user emotion.
4. The method of claim 1 , further comprising generating a plurality of synthetic voices from the database, wherein each synthetic voice in the plurality of synthetic voices is generated according to a respective selection policy.
5. The method of claim 1 , wherein a selection policy defines, for a particular phonetic category, which voice to use for synthesizing the synthesized speech.
6. The method of claim 1 , wherein the first portion of the voice data and the second portion of the voice data have a similar pitch range and fundamental frequency with respect to one another.
7. The method of claim 3 , wherein the synthesized speech is synthesized using selected voice units from the database, wherein the selected voice units comprise a first voice unit from the first portion of the voice data, and comprise a second voice unit from the second portion of the voice data.
8. The method of claim 7 , wherein the synthesized speech is synthesized without parameterizing the first portion of the voice data and without parameterizing the second portion of the voice data.
9. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, result in the processor performing operations comprising:
storing, in a database, voice data according to user emotions;
identifying, from user speech, a user emotion;
identifying, via at least one processor and according to the user emotion, a first portion of the voice data, wherein the first portion of the voice data comprises a first emotional content for a first speaker;
identifying, via the at least one processor and according to the user emotion, a second portion of the voice data, wherein the second portion of the voice data comprises a second emotional content for a second speaker; and
synthesizing synthesized speech using the first portion of the voice data and the second portion of the voice data.
10. The system of claim 9 , wherein the first portion of the voice data comprises first text-to-speech voice data and wherein the second portion of the voice data comprises second text-to-speech voice data.
11. The system of claim 9 , wherein the synthesized speech corresponds to the user emotion.
12. The system of claim 9 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising generating a plurality of synthetic voices from the database, wherein each synthetic voice in the plurality of synthetic voices is generated according to a respective selection policy.
13. The system of claim 9 , wherein a selection policy defines, for a particular phonetic category, which voice to use for synthesizing the synthesized speech.
14. The system of claim 11 , wherein the synthesized speech is synthesized using selected voice units from the database, wherein the selected voice units comprise a first voice unit from the first portion of the voice data, and comprise a second voice unit from the second portion of the voice data.
15. The system of claim 14 , wherein the synthesized speech is synthesized without parameterizing the first portion of the voice data and without parameterizing the second portion of the voice data.
16. A device having instructions stored which, when executed by a processor, result in the processor performing operations comprising:
storing, in a database, voice data according to user emotions;
identifying, from user speech, a user emotion;
identifying, via at least one processor and according to the user emotion, a first portion of the voice data, wherein the first portion of the voice data comprises a first emotional content for a first speaker;
identifying, via the at least one processor and according to the user emotion, a second portion of the voice data, wherein the second portion of the voice data comprises a second emotional content for a second speaker; and
synthesizing synthesized speech using the first portion of the voice data and the second portion of the voice data.
17. The device of claim 16 , wherein the first portion of the voice data comprises first text-to-speech voice data and wherein the second portion of the voice data comprises second text-to-speech voice data.
18. The device of claim 16 , wherein the synthesized speech using the first portion of the voice data and the second portion of the voice data yields synthesized speech that corresponds to the user emotion.
19. The device of claim 16 , wherein the synthesizing of the speech is performed using selected voice units from the database, wherein the selected voice units comprise a first voice unit from the first portion of the voice data, and comprise a second voice unit from the second portion of the voice data.
20. The device of claim 19 , wherein the synthesized speech is synthesized without parameterizing the first portion of the voice data and without parameterizing the second portion of the voice data.