System and method for 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:
combining a first database of first text-to-speech voice units and a second database of second text-to-speech voice units, the first text-to-speech voice units originating from a different speaker than the second text-to-speech voice units, to yield a combined database;
storing the combined database as if the combined database were from a single speaker;
determining a selection policy based on a current emotional context;
selecting from the combined database, based on the selection policy, voice units of a phonetic category for a synthetic voice, to yield selected voice units, wherein the selected voice units comprise a first voice unit from the first text-to-speech voice units and a second voice unit from the second text-to-speech voice units; and
synthesizing speech based on the selected voice units.
2. The method of claim 1 , wherein the speech is synthesized without parameterizing the first text-to-speech voice units and the second text-to-speech voice units.
3. The method of claim 1 , wherein the selection policy defines, for a particular phonetic category, from which text-to-speech voice to select the voice units.
4. The method of claim 1 , wherein the first text-to-speech voice units and the second text-to-speech voice units are in distinct styles of speaking.
5. The method of claim 1 , further comprising generating a plurality of synthetic voices from the combined database, wherein each synthetic voice in the plurality of synthetic voices is generated based on a respective selection policy.
6. The method of claim 5 , wherein the plurality of synthetic voices comprises one of a foreign language voice and a regional dialect voice.
7. The method of claim 1 , wherein the first text-to-speech voice units and the second text-to-speech voice units have a similar pitch range and fundamental frequency.
8. 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:
combining a first database of first text-to-speech voice units and a second database of second text-to-speech voice units, the first text-to-speech voice units originating from a different speaker than the second text-to-speech voice units, to yield a combined database;
storing the combined database as if the combined database were from a single speaker;
determining a selection policy based on a current emotional context;
selecting from the combined database, based on the selection policy, voice units of a phonetic category for a synthetic voice, to yield selected voice units, wherein the selected voice units comprise a first voice unit from the first text-to-speech voice units and a second voice unit from the second text-to-speech voice units; and
synthesizing speech based on the selected voice units.
9. The system of claim 8 , wherein synthesizing of the speech is performed without parameterizing the first text-to-speech voice units and the second text-to-speech voice units.
10. The system of claim 8 , wherein the selection policy defines, for a particular phonetic category, from which text-to-speech voice to select the voice units.
11. The system of claim 8 , wherein the first text-to-speech voice units and the second text-to-speech voice units are in distinct styles of speaking.
12. The system of claim 8 , wherein synthesizing of the speech further comprises generating a plurality of synthetic voices from the combined database, wherein each synthetic voice in the plurality of synthetic voices is generated based on a respective selection policy.
13. The system of claim 12 , wherein the plurality of synthetic voices comprises one of a foreign language voice and a regional dialect voice.
14. The system of claim 8 , wherein the first text-to-speech voice units and the second text-to-speech voice units have a similar pitch range and fundamental frequency.
15. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
combining a first database of first text-to-speech voice units and a second database of second text-to-speech voice units, the first text-to-speech voice units originating from a different speaker than the second text-to-speech voice units, to yield a combined database;
storing the combined database as if the combined database were from a single speaker;
determining a selection policy based on a current emotional context;
selecting from the combined database, based on the selection policy, voice units of a phonetic category for a synthetic voice, to yield selected voice units, wherein the selected voice units comprise a first voice unit from the first text-to-speech voice units and a second voice unit from the second text-to-speech voice units; and
synthesizing speech based on the selected voice units.