Speech synthesis apparatus with output editing

• US 5,842,167 A
• Filed: 05/21/1996
• Issued: 11/24/1998
• Est. Priority Date: 05/29/1995
• Status: Expired due to Term

• Current Assignee: Sanyo Electric Company Limited (Panasonic Holdings Corporation)
• Original Assignee: Sanyo Electric Company Limited (Panasonic Holdings Corporation)
• Inventors: Takeda, Shoji, Ochiiwa, Masashi, Ohnishi, Hiroki, Miyatake, Masanori, Izumi, Takashi, Yumura, Takeshi
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Wieland, Susan
• Application Number:
  US08/653,075
• Time in Patent Office: 917 Days
• Field of Search: 395/2.7, 395/2.77, 395/2.87, 395/2.69, 395/2.44, 704/260, 704/261, 704/268, 704/278, 704/235, 704/276
• US Class Current: 704/260
• 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

A speech synthesis apparatus for synthesizing speech from text data, having a voice characteristic, a tone, a rhythm, etc. which corresponds to the contents of edition on the text data displayed on a screen, by converting a volume, a speed, a pitch, a voice characteristic, etc. of a voice on judging the contents of the edition, such as an edition of a size, a spacing, a font and so on of a character, on the text data displayed on a screen.

Claims

1. A speech synthesis apparatus, comprising:

means for inputting text data and data indicating editing of the appearance of the character of said text data, wherein said editing is character attribution which is expressible by the visual appearance of said editing;

means for synthesizing speech from said text data having an elocution mode corresponding to the editing of the appearance of the character of said text data;

a display screen for displaying the appearance of the character of said text data; and

means for displaying said inputted text data;

means for editing the appearance of the character of the text data displayed by said displaying means on said display screen according to the appearance data of speech, including emphasis expression or emotional expression;

means for synthesizing speech corresponding to the appearance of the character of the text data edited by the text data editing means having an output mode corresponding to the contents of the editing on the appearance of the character of said text data when synthesizing speech from the text data input by the text data inputting means.

2. A speech synthesis apparatus as set forth in claim 1, wherein said text data inputting means includes means for recognizing handwritten characters.

3. A speech synthesis apparatus as set forth in claim 1, further comprising means for processing speech language by analyzing said text data input by said text data inputting means to generate prosodic data of speech to be synthesize said text data, and

wherein said text data displaying means initially displays without editing the text data in a condition that corresponds to the prosodic data generated by said speech language processing means.

4. A speech synthesis apparatus as set forth in claim 3, wherein said text data inputting means includes means for recognizing handwritten characters.

5. A speech synthesis apparatus as set forth in claim 1 wherein said appearance of the character of said text data is the character size.

6. A speech synthesis apparatus as set forth in claim 1 wherein said appearance of the character of said text data is the character spacing.

7. A speech synthesis apparatus as set forth in claim 1 wherein said appearance of the character of said text data is the character height.

8. A speech synthesis apparatus as set forth in claim 1 wherein said appearance of the character of said text data is the character color.

9. A speech synthesis apparatus as set forth in claim 1 wherein said appearance of the character of said text data is the character thickness.

10. A speech synthesis apparatus as set forth in claim 1 wherein said data indicating editing of the appearance of said text data character is an underline of the character.

11. A speech synthesis apparatus as set forth in claim 1 wherein said data indicating editing of the appearance of said text data character is the data indicating editing of the type of the font.

12. A speech synthesis apparatus as set forth in claim 11 wherein said data indicating editing of the appearance of the character is the font being italic.

13. A speech synthesis apparatus as set forth in claim 11 wherein said data indicating editing of the appearance of the character is the font being Gothic.

14. A speech synthesis apparatus as set forth in claim 1 wherein said data indicating editing of the appearance of the character is the font being round.

15. A speech synthesis apparatus as set forth in claim 1 wherein said data indicating editing of the appearance of the character is a command.

16. Apparatus for producing synthesized speech comprising:

inputting means for inputting text data to be produced as synthesized speech;

an analyzer for associating the inputted text data into characters of the synthesized speech to be produced;

a display for visually displaying said characters;

said inputting means inputting editing data to edit the visual appearance of the display of said characters, the editing data editing the visual display of said characters corresponding to desired audio characteristics of the synthesized speech to be produced; and

speech synthesizing means responsive to the edited versions of said characters for producing the synthesized speech with the desired audio characteristics corresponding to the displayed edited text data.

17. A speech synthesis apparatus as set forth in claim 16 wherein said appearance of the character is the character size.

18. A speech synthesis apparatus as set forth in claim 16 wherein said appearance of the character the character spacing.

19. A speech synthesis apparatus as set forth in claim 16 wherein said appearance of the character is the character height.

20. A speech synthesis apparatus as set forth in claim 16 wherein said appearance of the character is the character color.

21. A speech synthesis apparatus as set forth in claim 16 wherein said appearance of the character is the character thickness.

22. A speech synthesis apparatus as set forth in claim 16 wherein said data indicating editing of the appearance of the character is an underline of the character.

23. A speech synthesis apparatus as set forth in claim 16 wherein said data indicating editing of the appearance of the character is the type of the font.

24. A speech synthesis apparatus as set forth in claim 23 wherein said data indicating editing of the appearance of the character is the font being italic.

25. A speech synthesis apparatus as set forth in claim 23 wherein said data indicating editing of the appearance of the character is the font being Gothic.

26. A speech synthesis apparatus as set forth in claim 23 wherein said data indicating editing of the appearance of the character is the font being round.

27. A speech synthesis apparatus as set forth in claim 16 wherein said data indicating editing of the appearance of the character is a command.

28. A speech synthesis apparatus, comprising:

means for displaying text data on said display screen which corresponds to the contents of output synthesized speech;

means or editing the visual appearance of the character of the text data displayed on the screen; and

means for synthesizing speech having an output corresponding to the edited appearance of the character of said text data by the text data editing means.

29. A speech synthesis apparatus as set forth in claim 28 wherein said appearance of the character is the character size.

30. A speech synthesis apparatus as set forth in claim 28 wherein said appearance of the character is the character spacing.

31. A speech synthesis apparatus as set forth in claim 28 wherein said appearance of the character is the character height.

32. A speech synthesis apparatus as set forth in claim 28 wherein said appearance of the character is the character color.

33. A speech synthesis apparatus as set forth in claim 28 wherein said appearance of the character is the character thickness.

34. A speech synthesis apparatus as set forth in claim 28 wherein said data indicating editing of the appearance of the character is the underline.

35. A speech synthesis apparatus as set forth in claim 28 wherein said data indicating editing of the appearance of the character is the type of the font.

36. A speech synthesis apparatus as set forth in claim 35 wherein said data indicating editing of the appearance of the character is the font to be italic.

37. A speech synthesis apparatus as set forth in claim 35 wherein said data indicating editing of the appearance of the character is the font to be Gothic.

38. A speech synthesis apparatus as set forth in claim 28 wherein said data indicating editing of the appearance of the character is the font to be round.

39. A speech synthesis apparatus as set forth in claim 28 wherein said data indicating editing of the appearance of the character is a command.