Method and system for parametric speech synthesis
Embodiments of the present systems and methods may provide techniques for synthesizing speech in any voice in any language in any accent. For example, in an embodiment, a text-to-speech conversion system may comprise a text converter adapted to convert input text to at least one phoneme selected from a plurality of phonemes stored in memory, a machine-learning model storing voice patterns for a plurality of individuals and adapted to receive the at least one phoneme and an identity of a speaker and to generate acoustic features for each phoneme, and a decoder adapted to receive the generated acoustic features and to generate a speech signal simulating a voice of the identified speaker in a language.
1. A text-to-speech conversion system comprising;
a text converter adapted to convert input text to at least one phoneme selected from a plurality of phonemes stored in memory;
a machine-learning model storing voice patterns for a plurality of individuals and adapted to receive the at least one phoneme and an identity of a speaker and to generate and enhance acoustic features for each phoneme, wherein the voice patterns comprise a matrix of components equal to a number of components of a production approach to speech synthesis times a number of components of an acoustic approach to speech synthesis, and wherein the enhanced acoustic features comprise at least one of spectral enhancement or focal enhancement; and
a decoder adapted to receive the generated acoustic features and to generate a speech signal simulating a voice of the identified speaker in a language.
2. The system of claim 1 , wherein the plurality of phonemes stored in memory comprise phonemes of the International Phonetic Alphabet and silence and breath.
3. The system of claim 1 , wherein the machine-learning model comprises a neural network model.
4. The system of claim 1 , wherein spectral enhancement comprises increasing a peak of a spectral envelope or decreasing a trough of the spectral envelope and focal enhancement comprises emphasizing the difference between a first frame and a second frame.
5. The system of claim 1 , wherein the text converter is further adapted to detect a language of the input text to be converted.
6. The system of claim 5 , wherein the language of the input text to be converted is detected using an n-gram approach.
7. The system of claim 1 , wherein the generated acoustic features include accent acoustic features and the generated speech signal further simulates a voice of the identified speaker in a language and in an accent.
8. The system of claim 7 , wherein the accent corresponds to a native accent of the identified speaker.
9. A method for text-to-speech conversion implemented in a computer system comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, the method comprising:
converting, at the computer system, input text to at least one phoneme selected from a plurality of phonemes stored in memory;
storing, in a machine-learning model t the computer system, voice patterns for a plurality of individuals, receiving, at the machine-learning model at the computer system, the at least one phoneme and an identity of a speaker, and generating and enhancing, with the machine-learning model at the computer system, acoustic features for each phoneme, wherein the voice patterns comprise a matrix of components equal to a number of components of a production approach to speech synthesis times a number of components of an acoustic approach to speech synthesis, and wherein enhancing acoustic features comprises at least one of spectral enhancement or focal enhancement; and
receiving, at the computer system, the generated acoustic features and generating, at the computer system, a speech signal simulating a voice of the identified speaker in a language.
10. The method of claim 9 , wherein the plurality of phonemes stored in memory comprise phonemes of the International Phonetic Alphabet and silence and breath.
11. The method of claim 9 , wherein the machine-learning model comprises a neural network model.
12. The method of claim 9 , herein spectral enhancement comprises increasing a peak of a spectral envelope or decreasing a trough of the spectral envelope and focal enhancement comprises emphasizing the difference between a first frame and a second frame.
13. The method of claim 9 , further comprising detecting, at the computer system, a language of the input text to be converted.
14. The method of claim 13 , herein the language of the input text to be converted is detected using an n-gram approach.
15. The method of claim 9 , wherein the generated acoustic features include accent acoustic features and the generated speech signal further simulates a voice of the identified speaker in a language and in an accent.
16. The method of claim 15 , wherein the accent corresponds to a native accent of the identified speaker.
17. The system of claim 1 , wherein the production approach comprises phones, coarticulation, prosody from linguistic features, and prosody from extra-linguistic features and the acoustic approach comprises spectrum, power, duration, and pitch.
18. The method of claim 9 , wherein the production approach comprises phones, coarticulation, prosody from linguistic features, and prosody from extra-linguistic features and the acoustic approach comprises spectrum, power, duration, and pitch.