Individualization of voice output by matching synthesized voice target voice

• US 7,664,645 B2
• Filed: 03/11/2005
• Issued: 02/16/2010
• Est. Priority Date: 03/12/2004
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: SVOX AG (Microsoft Corporation)
• Inventors: Hain, Horst-Udo, Lukas, Klaus
• Primary Examiner(s): Chawan; Vijay B
• Application Number:
  US11/077,153
• Publication Number:
  US 20050203743A1
• Time in Patent Office: 1,803 Days
• Field of Search: 704/231, 704/251, 704/220, 704270-278, 704/250, 704/269
• US Class Current: 704/269
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser

Abstract

The voice of a synthesized voice output is individualized and matched to a user voice, the voice of a communication partner or the voice of a famous personality. In this way mobile terminals in particular can be originally individualized and text messages can be read out using a specific voice.

Claims

1. A method embodied in a communication apparatus for speech synthesis, the method comprising:

capturing speech signals related to one or more target voices and calculating transformation values of each of the target voices by evaluating voice features of the speech signals;

assigning a unique communication identifier to the transformation values for each respective target voice; and

matching a synthesized voice of the communication apparatus to one of the one or more target voices based on transformation values assigned to a selected communication identifier.

2. A method according to claim 1, wherein at least one of the one or more target voices is a voice of a user of the communication apparatus.

3. A method according to claim 2, further comprising obtaining data for matching the synthesized voice to at least one of the one or more target voices from speech signals spoken into the communication apparatus by the user.

4. A method according to claim 3, wherein said obtaining uses the speech signals spoken into the communication device by the user for communication to obtain the data for matching the synthesized voice to the at least one target voice.

5. A method according to claim 4, further comprising:

storing the speech signals during the communication,

wherein said obtaining of the data for matching the synthesized voice to the at least one target voice uses the stored speech signals after the communication has ended.

6. A method according to claim 1, wherein at least one of the one or more target voices is a voice of a communication partner of a user of the communication apparatus.

7. A method according to claim 6, further comprising obtaining data for matching the synthesized voice to at least one of the one or more target voices from speech signals transmitted by the communication partner for communication with the user of the communication apparatus.

8. A method according to claim 7, further comprising:

storing the speech signals during the communication,

wherein said obtaining of the data for matching the synthesized voice to the at least one target voice uses the stored speech signals after the communication has ended.

9. A method according to claim 1, further comprising downloading data for matching the synthesized voice to the target voice via a network.

10. A method according to claim 1, wherein the communication apparatus is at least one of embedded hardware, a mobile terminal and communication apparatus with a mobile telephone function.

11. A communication apparatus for speech synthesis, comprising:

means for capturing speech signals related to one or more target voices;

means for calculating transformation values of each of the target voices by evaluating voice features of the speech signals;

means for assigning a unique communication identifier to the transformation values for each respective target voice; and

means for matching a synthesized voice of the communication apparatus for output of synthesized speech to one of the one or more target voices based on transformation values assigned to a selected communication identifier.

12. An apparatus according to claim 11, wherein the communication apparatus is at least one of embedded hardware, a mobile terminal and a communication apparatus with a mobile telephone function.

13. A computer readable medium encoded with a program for performing speech synthesis of a communication apparatus, the program when executed by a processor causes the processor to perform a method comprising:

capturing speech signals related to one or more target voices and calculating transformation values of each of the target voices by evaluating voice features of the speech signals;

assigning a unique communication identifier to the transformation values for each respective target voice; and

matching a synthesized voice of the communication apparatus to one of the one or more target voices based on transformation values assigned to a selected communication identifier.

14. A computer readable medium according to claim 13, wherein at least one of the one or more target voices is a voice of one of a user of the device and a communication partner of the user.

15. A computer readable medium according to claim 14, wherein said method further comprises obtaining data for matching the synthesized voice to at least one of the one or more target voices from speech signals spoken into the communication apparatus by one of the user and the communication partner of the user.

16. A computer readable medium according to claim 15, wherein said obtaining uses the speech signals spoken into the communication apparatus by the one of the user and the communication partner of the user for communication to obtain the data for matching the synthesized voice to the at least one target voice.

17. A computer readable medium according to claim 16, further comprising storing the speech signals during the communication,

wherein said obtaining of the data for matching the synthesized voice to the at least one target voice uses the stored speech signals after the communication has ended.

18. A method embodied in a communication apparatus for speech synthesis, the method comprising:

capturing speech signals related to one or more target voices and calculating warping values of each of the target voices by evaluating voice features of the speech signals;

assigning a unique communication identifier to the warping values for each respective target voice; and

matching a synthesized voice of the communication apparatus to one of the one or more target voices based on warping values assigned to a selected communication identifier.