Text-to-speech synthesis system

• US 7,099,826 B2
• Filed: 05/31/2002
• Issued: 08/29/2006
• Est. Priority Date: 06/01/2001
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Akabane, Makoto, Yano, Hajime, Yamada, Keiichi, Shiraishi, Goro, Kudo, Junichi, Tange, Akira
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US10/161,329
• Publication Number:
  US 20030023442A1
• Time in Patent Office: 1,551 Days
• Field of Search: None
• US Class Current: 704/260
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

The present invention is intended to provide a text-to-speech synthesis apparatus, including a storage for storing phoneme data of a plurality of speakers; a selector for selecting one of the plurality of speakers in accordance with an operation performed by a user; a searcher for searching the storage for phoneme data of the speaker selected by the selector; a text-to-speech synthesis processor for linking the phoneme data of the speaker retrieved by the searcher to convert input data into a synthetic speech; and a fee-charge controller for controlling a fee-charge operation for the user in accordance with the phoneme data selected by the selector. Consequently, the user can perform text-to-speech synthesis on the desired input data such as drama data by use of the obtained phoneme data.

Claims

1. A text-to-speech synthesis apparatus comprising:

storage means for storing phoneme data of a plurality of speaker voices;

selecting means for selecting one of said plurality of speaker voices in accordance with an operation performed by a user;

searching means for searching said storage means for phoneme data of the one speaker voice selected by said selecting means;

text-to-speech synthesis processing means for linking said phoneme data of said one speaker voice retrieved by said searching means to convert input data into a synthetic speech;

fee-charge control means for controlling a fee-charge operation for the user in accordance with said phoneme data of the one speaker voice selected by said selecting means; and

prepaid card loading means for accommodating a prepaid card, wherein said fee-charge control means updates fee-charge information in said prepaid card on a basis of fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.

2. The text-to-speech synthesis apparatus according to claim 1, wherein said fee-charge control means sends, to an external settlement center, fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.

3. The text-to-speech synthesis apparatus according to claim 1, wherein said storage means stores prosody data for each of said plurality of speaker voices, said searching means searches for said prosody data along with said phoneme data of the one speaker voice selected by said selecting means, and said text-to-speech synthesis processing means converts said input data into a synthetic speech on a basis of said searched phoneme data and said prosody data.

4. The text-to-speech synthesis apparatus according to claim 1, wherein said input data is at least one of voice data and text data.

5. The text-to-speech synthesis apparatus according to claim 1, further comprising input means for directly inputting said input data.

6. The text-to-speech synthesis apparatus according to claim 1, further comprising communication means for receiving said input data via a network.

7. The text-to-speech synthesis apparatus according to claim 1, wherein said storage means stores script data and said text-to-speech synthesis processing means links said phoneme data of said speaker voice searched by said searching means to convert said script data into a synthetic speech.

8. The text-to-speech synthesis apparatus according to claim 7, wherein said storage means stores said script data in a classified manner and said selecting means selects said script data along with said one speaker voice.

9. The text-to-speech synthesis apparatus according to claim 7, wherein said script data is at least one of voice data and text data.

10. A text-to-speech synthesis apparatus comprising:

selecting means for selecting a speaker voice as specified by a user;

transmitting means for transmitting to another apparatus speaker voice identification data for identifying said speaker voice selected by said selecting means;

receiving means for receiving phoneme data of said speaker voice corresponding to said speaker voice identification data transmitted by said transmitting means;

text-to-speech synthesis processing means for linking said phoneme data of said speaker voice received by said receiving means to convert input data into a synthetic speech;

fee-charge control means for controlling a fee-charge operation for said user in accordance with said phoneme data received by said receiving; and

prepaid card loading means for accommodating a prepaid card, wherein said fee-charge control means updates fee-charge information in said prepaid card on a basis of fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.

11. The text-to-speech synthesis apparatus according to claim 10, wherein said fee-charge control means sends, to an external settlement center, fee-charge data corresponding to said phoneme data to be received by said receiving means.

12. The text-to-speech synthesis apparatus according to claim 10, wherein said input data is at least one of voice data and text data.

13. The text-to-speech synthesis apparatus according to claim 10, further comprising input means for directly inputting said input data.

14. The text-to-speech synthesis apparatus according to claim 10, further comprising communication means for receiving said input data via a network.

15. The text-to-speech synthesis apparatus according to claim 10, wherein said selecting means selects script data as specified by said user;

said transmitting means transmits, to another apparatus, script identification data for identifying said script data selected by said selecting means;

said receiving means receives phoneme data of a speaker voice corresponding to said speaker voice identification data transmitted by said transmitting means and said script data corresponding to said script identification data;

said text-to-speech synthesis processing means links said phoneme data of said speaker voice received by said receiving means to convert said script data into a synthetic speech; and

said fee-charge control means controls a fee-charge operation for said user on the basis of said phoneme data of said speaker voice received by said receiving means and said script data.

16. The text-to-speech synthesis apparatus according to claim 15, wherein said receiving means receives said synthetic speech of said script data obtained by said another apparatus on the basis of said speaker voice identification data and said script identification data transmitted by said transmitting means and said fee-charge control means controls a fee-charge control operation for said user in accordance with said synthetic speech received by said receiving means.

17. The text-to-speech synthesis apparatus according to claim 15, wherein said script data is at least one of voice data and text data.

18. A text-to-speech synthesis apparatus comprising:

a memory for storing phoneme data of a plurality of speaker voices;

a selecting section for selecting any one of said plurality of speaker voices as specified by a user;

a search section for searching said memory for the phoneme data of the one speaker voice selected by said selecting section;

a text-to-speech synthesis processing section for linking said phoneme data of said one speaker voice retrieved by said search section to convert script data into a synthetic speech;

a fee-charge control section for controlling a fee-charge operation for said user in accordance with said phoneme data of the one speaker voice selected by said selecting section;

a storage section for accumulating said synthetic speech converted from said script data on the basis of the phoneme data of said plurality of speaker voices;

a reproducing section for retrieving said synthetic speech of said one speaker voice selected by said selecting section and reproducing said synthetic speech; and

prepaid card loading means for accommodating a prepaid card, wherein said fee-charge control means updates fee-charge information in said prepaid card on a basis of fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.

19. The text-to-speech synthesis apparatus according to claim 18, wherein said fee-charge control section sends, to an external settlement center, fee-charge data corresponding to the phoneme data of the one speaker voice selected by said selecting section.

20. The text-to-speech synthesis apparatus according to claim 18, wherein said memory stores prosody data for each of said plurality of speaker voices, said search section searches for said prosody data along with said phoneme data of said one speaker voice selected by said selecting section;

and said text-to-speech synthesis processing section converts said script data into a synthetic speech on the basis of said user-specified phoneme data and prosody data.

21. The text-to-speech synthesis apparatus according to claim 18, wherein said script data is at least one of voice data and text data.

22. The text-to-speech synthesis apparatus according to claim 18, further comprising an input section for directly inputting said script data.

23. The text-to-speech synthesis apparatus according to claim 18, further comprising a communication section for receiving said script data via a network.

24. The text-to-speech synthesis apparatus according to claim 18, wherein said memory stores said script data and said text-to-speech synthesis processing section links said phoneme data of said one speaker voice retrieved by said search section to convert said script data into a synthetic speech.

25. The text-to-speech synthesis apparatus according to claim 24, wherein said memory stores said script data in a classified manner and said selecting section selects said script data along with said one speaker voice.

26. The text-to-speech synthesis apparatus according to claim 24, wherein said script data is at least one of voice data and text data.

28. The text-to-speech synthesis apparatus according to claim 24, wherein said fee-charge control section sends, to an external settlement center, fee-charge data corresponding to said phoneme data received by said receiving section.

29. The text-to-speech synthesis apparatus according to claim 24, wherein said script data is at least one of voice data and text data.

30. The text-to-speech synthesis apparatus according to claim 24, further comprising an input section for directly inputting said script data.

31. The text-to-speech synthesis apparatus according to claim 24, further comprising a communication section for receiving said script data via a network.

32. The text-to-speech synthesis apparatus according to claim 24, wherein said selecting section selects script data as specified by a user;

said transmitting section transmits, to said another apparatus, script identification data for identifying script data corresponding to the speaker voice selected by said selecting section;

said receiving section receives phoneme data of a speaker voice corresponding to said speaker voice identification data transmitted by said transmitting section and said script data corresponding to said script identification data;

said text-to-speech synthesis processing section links said phoneme data of said speaker voice received by said receiving section to convert said script data into a synthetic speech; and

said fee-charge control section controls a fee-charge operation for said user in accordance with said phoneme data of said speaker voice received by said receiving section and said script data.

33. The text-to-speech synthesis apparatus according to claim 32, wherein said receiving section receives the synthetic speech of said script data generated on said another apparatus on the basis of said speaker voice identification data and said script identification data transmitted by said transmitting section and said fee-charge control section controls a fee-charge operation for said user in accordance with said synthetic speech received by said receiving section.

34. The text-to-speech synthesis apparatus according to claim 32, wherein said script data is at least one of voice data and text data.

27. A text-to-speech synthesis apparatus comprising:

a selecting section for selecting a speaker voice as specified by user;

a transmitting section for transmitting, to another apparatus, speaker voice identification data for identifying said speaker voice selected by said selecting section;

a receiving section for receiving phoneme data of the speaker voice corresponding to said speaker voice identification data transmitted by said transmitting section and a synthetic speech of said speaker voice;

a text-to-speech synthesis processing section for linking said phoneme data of said speaker voice received by said receiving section to convert script data into a synthetic speech;

a reproducing section for reproducing said synthetic speech;

a fee-charge control section for controlling a fee-charge operation for said user in accordance with said phoneme data received by said receiving section; and

prepaid card loading means for accommodating a prepaid card, wherein said fee-charge control means updates fee-charge information in said prepaid card on a basis of fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.

35. A text-to-speech synthesis method comprising the acts of:

selecting one of plurality of speaker voices in accordance with an operation performed by a user;

searching phoneme data of said plurality of speaker voices for phoneme data of any one of said plurality of speaker voices specified by a user;

linking said phoneme data of said one speaker voice retrieved in said searching step to convert input data into a synthetic speech;

controlling a fee-charge operation for the user in accordance with said phoneme data selected in said selecting step; and

prepaid card loading means for accommodating a prepaid card, wherein said fee-charge control means updates fee-charge information in said prepaid card on a basis of fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.

36. A recording medium storing a text-to-speech synthesis program which, when implemented, comprises acts of:

selecting one of plurality of speaker voices in accordance with an operation performed by a user;

searching phoneme data of said plurality of speaker voices for phoneme data of any one of said plurality of speaker voices specified by a user;

linking said phoneme data of said one speaker voice retrieved in said searching step to convert input data into a synthetic speech;

controlling a fee-charge operation for the user in accordance with said phoneme data selected in said selecting step; and

prepaid card loading means for accommodating a prepaid card, wherein said fee-charge control means updates fee-charge information in said prepaid card on a basis of fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.

37. A text-to-speech synthesis method comprising acts of:

selecting a speaker voice as specified by a user;

transmitting to another apparatus speaker voice identification data for identifying said speaker voice selected in said selecting step;

receiving phoneme data of said speaker voice corresponding to said speaker voice identification data transmitted in said transmitting step;

linking said phoneme data of said speaker voice received in said receiving step to convert input data into a synthetic speech;

controlling a fee-charge operation for said user in accordance with said phoneme data received in said receiving step; and

prepaid card loading means for accommodating a prepaid card, wherein said fee-charge control means updates fee-charge information in said prepaid card on a basis of fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.

38. A recording medium storing a text-to-speech synthesis program which, when implemented, comprises acts of:

selecting a speaker voice as specified by a user;

transmitting to another apparatus speaker voice identification data for identifying said speaker voice selected in said selecting step;

receiving phoneme data of said speaker voice corresponding to said speaker voice identification data transmitted in said transmitting step;

linking said phoneme data of said speaker voice received in said receiving step to convert input data into a synthetic speech;

controlling a fee-charge operation for said user in accordance with said phoneme data received in said receiving step; and

prepaid card loading means for accommodating a prepaid card, wherein said fee-charge control means updates fee-charge information in said prepaid card on a basis of fee-charge data corresponding to said phoneme data of the one speaker voice selected by said selecting means.