Providing personalized voice front for text-to-speech applications

• US 20060095265A1
• Filed: 10/29/2004
• Published: 05/04/2006
• Est. Priority Date: 10/29/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Zhao, Yong, Zhao, Sheng, Chu, Min
• Granted Patent: US 7,693,719 B2
• Time in Patent Office: Days
• US Class Current: 704/268
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 2021/0135 Voice conversion or morphing

Abstract

A method for synthesizing speech from text includes receiving one or more waveforms characteristic of a voice of a person selected by a user, generating a personalized voice font based on the one or more waveforms, and delivering the personalized voice font to the user'"'"'s computer, whereby speech can be synthesized from text, the speech being in the voice of the selected person, the speech being synthesized using the personalized voice font. A system includes a text-to-speech (TTS) application operable to generate a voice font based on speech waveforms transmitted from a client computer remotely accessing the TTS application.

Claims

1. A method for synthesizing speech from text, the speech being in a specified voice, the method comprising:

receiving one or more waveforms characteristic of a voice of a person selected by a user;

generating a personalized voice font based on the one or more waveforms;

delivering the personalized voice font to the user'"'"'s computer, whereby speech can be synthesized from text, the speech being in the voice of the selected person, the speech being synthesized using the personalized voice font.

2. A method as recited in claim 1 wherein the receiving comprises receiving the one or more waveforms via a network connected to the user'"'"'s computer.

3. A method as recited in claim 1 wherein delivering comprises transmitting the voice font to the user'"'"'s computer via a network.

4. A method as recited in claim 1 further comprising certifying the identity of the user.

5. A method as recited in claim 1 wherein the voice font is embodied in a data structure that associates basic phonetic units with corresponding speech segments.

6. A method as recited in claim 1 wherein the selected person is the user.

7. A method as recited in claim 1 further comprising enabling the user to select the personalized voice font from a plurality of voice fonts.

8. A method as recited in claim 1 further comprising delivering a text-to-speech (TTS) engine to the user'"'"'s computer, the TTS engine being operable to synthesize the speech based on the personalized voice font.

9. A method as recited in claim 1 further comprising requesting an additional waveform from the selected person.

10. A method as recited in claim 1, wherein the one or more waveforms are based on one or more prepared statements spoken by the selected person, the method further comprising generating a script to request one or more additional statements from the selected person, wherein the additional statements cover one or more basic phonetic units that are not covered by the prepared statements.

11. A method as recited in claim 1 wherein the personalized voice font is configured for use by a text-to-speech (TTS) engine that communicates with a text-based application program to synthesize speech based on text from the text-based application program.

12. A method as recited in claim 1 wherein delivering comprise transmitting the personalized voice font to at least one of the following devices:

a personal digital assistant;

a cellular phone;

a desktop computer;

a laptop computer;

a handheld computer.

13. A computer-readable medium having computer-executable instructions that, when executed, cause a computer to perform a process comprising:

receiving via a microphone at a user'"'"'s computer, audio input corresponding to a voice of a speaker;

encoding the audio input into a waveform;

transmitting the waveform to a text-to-speech (TTS) engine residing on a remote computer that is in communication with the user'"'"'s computer;

instructing the TTS engine to generate a personalized voice font based on the waveform;

transmitting text to the TTS engine;

receiving synthesized speech from the TTS engine, the synthesized speech corresponding to the text and being synthesized with a personalized voice font representative of the speaker'"'"'s voice.

14. A computer-readable medium as recited in claim 13, the process further comprising instructing the TTS engine to select the personalized voice font from a plurality of voice fonts.

15. A computer-readable medium as recited in claim 13, the process further comprising transmitting the personalized voice font to either the user'"'"'s computer or another computer in communication with the remote computer.

16. A computer-readable medium as recited in claim 13 wherein receiving audio input comprises receiving spoken statements from the person, the statements being prepared statements that cover a range of basic phonetic units.

17. A computer-readable medium as recited in claim 13, the process further comprising generating a script having statements for the speaker.

18. A computer-readable medium as recited in claim 13, the process further comprising generating, by the TTS engine, the personalized voice font.

19. A computer-readable medium as recited in claim 13, the process further comprising:

requesting a voice font from a set of celebrity voice fonts and a set of private voice fonts;

receiving the requested voice font;

applying the requested voice font to text such that speech corresponding to the text is synthesized using the selected voice font.

20. A computer-readable medium as recited in claim 13, the process further comprising certifying the identity of the speaker.

21. A computer-readable medium as recited in claim 13, wherein the speaker is selected from a group comprising:

the user;

a friend of the user;

a family member of the user;

a popular person.

22. A computer-readable medium as recited in claim 13, the process further comprising outputting audio based on the synthesized speech at the user'"'"'s computer.

23. A system comprising a text-to-speech (TTS) application operable to generate a voice font based on speech waveforms transmitted from a client computer remotely accessing the TTS application.

24. A system as recited in claim 23 further comprising a TTS web service controlling the client computer'"'"'s access to the TTS application.

25. A system as recited in claim 23 wherein the TTS application comprises one or more celebrity voice fonts based on speech from celebrities.

26. A system as recited in claim 23 wherein the TTS application comprises one or more personalized voice fonts that can be selected for use by a user of the client computer.

27. A system as recited in claim 23 wherein the TTS application comprises one or more voice fonts that can be downloaded to another computer in communication with the TTS application.

28. A system as recited in claim 23 wherein the TTS application comprises a TTS engine, the TTS engine including a speech synthesizer operable to convert specified text to speech in a voice corresponding to the generated voice font.