Voice synthesizing method and voice synthesizer performing the same

• US 7,113,909 B2
• Filed: 07/31/2001
• Issued: 09/26/2006
• Est. Priority Date: 06/11/2001
• Status: Expired due to Term

• Current Assignee: Maxell, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Nagamatsu, Kenji, Kitahara, Yoshinori, Nukaga, Nobuo
• Primary Examiner(s): Chawan, Vijay B.
• Application Number:
  US09/917,829
• Publication Number:
  US 20020188449A1
• Time in Patent Office: 1,883 Days
• Field of Search: 704/258, 704/260, 704/261, 704/268, 704/270, 704/267, 434/185
• US Class Current: 704/258
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

A stereotypical sentence is synthesized into a voice of an arbitrary speech style. A third party is able to prepare prosody data and a user of a terminal device having a voice synthesizing part can acquire the prosody data. The voice synthesizing method determines a voice-contents identifier to point to a type of voice contents of a stereotypical sentence, prepares a speech style dictionary including speech style and prosody data which correspond to the voice-contents identifier, selects prosody data of the synthesized voice to be generated from the speech style dictionary, and adds the selected prosody data to a voice synthesizer 13 as voice-synthesizer driving data to thereby perform voice synthesis with a specific speech style. Thus, a voice of a stereotypical sentence can be synthesized with an arbitrary speech style.

Claims

1. A voice synthesizing method comprising steps of:

selecting a speech style for a voice to be synthesized;

determining a voice-contents of a stereotypical sentence to be synthesized;

selecting prosody data of said stereotypical sentence, which corresponds to the selected voice-contents and which is in the same language as the voice-contents, from a speech style dictionary which corresponds to the selected speech style; and

inputting said selected prosody data to a voice-synthesizer that performs voice synthesis of the selected prosody data and outputs a voice of the stereotypical sentence of the selected speech style.

2. The voice synthesizing method according to claim 1, wherein said prosody data comprises at least a sequence of phonetic symbols that are voice elements into which said voice contents of said stereotypical sentence are composed, and information on a duration, an intensity and power of each of the voice elements constituting said sequence of phonetic symbols.

3. A voice synthesizing method according to claim 1, wherein the speech style further includes foreign languages;

and

the step of selecting prosody data selects a stereotypical sentence in said foreign languages, which is different from the language of the voice-contents, when the foreign language is selected as the speech style.

4. A voice synthesizer according to claim 1, further comprising:

a step of determining a word to be inserted in a replaceable part in the stereotypical sentences and calculates a prosody data of the word; and

synthesizes the voice signal by inserting the prosody data of the input word to the replaceable part in the stereotypical sentences.

5. A voice synthesizer according to claim 1, wherein the voice-contents is selected by selecting a voice-content identifier identifying voice contents.

6. A voice synthesizer, comprising:

a memory for storing a speech style dictionary in which speech-style information that specifies a speech style for a voice to be synthesized and prosody data of a plurality of stereotypical sentences each of which corresponds to predetermined voice contents and which is in the same language as the voice-contents are associated with each other;

pointing means for pointing to one said predetermined voice-contents and one said speech style of a voice to be synthesized at a time of voice synthesis; and

said voice synthesizing part selecting said prosody data of the stereotypical sentence which corresponds to the pointed voice-contents and the pointed speech style from said speech style dictionary and converting said prosody data to a voice signal.

7. The voice synthesizer according to claim 6, wherein said prosody data comprises at least a sequence of phonetic symbols that are voice elements into which said voice contents of said stereotypical sentence are composed, and information on a duration, an intensity and power of each of the voice elements constituting said sequence of phonetic symbols.

8. A cellular phone having a voice synthesizer as recited in claim 6.

9. A voice synthesizer according to claim 6, wherein the speech style further includes foreign languages;

and

the voice synthesizing part selects a stereotypical sentence in said foreign languages, which is different from the language of the voice-contents, when the foreign language is selected as the speech style.

10. A voice synthesizer according to claim 6, wherein the memory further stores information of the stereotypical sentences each of which associated to the corresponds prosody data.

11. A voice synthesizer according to claim 6, wherein the voice synthesizing part determines a word to be inserted in a replaceable part in the stereotypical sentences and calculates a prosody data of the word, and synthesizes the voice signal by inserting the prosody data of the input word to the replaceable part in the stereotypical sentences.

12. A prosody-data distributing method comprising steps of:

receiving an input specifying a speech style;

preparing a speech style dictionary that corresponds to the specified speech style which includes prosody data of a plurality of stereotypical sentences each of which corresponds to a predetermined voice contents and is in the same language as the voice-contents; and

supplying said speech style dictionary to a server provided in a communication network or a terminal device connected via said server;

so that the server and the terminal device can perform voice synthesis of the stereotypical sentence, when an input of specifying voice-content and speech style is input, using the supplied speech style dictionary.

13. The prosody-data distributing method according to claim 12, wherein said prosody data comprises at least a sequence phonetic symbols that are voice elements into which said voice contents of and said stereotypical sentence are composed, and information on a duration, an intensity and power of each of the voice elements constituting said sequence of phonetic symbols.

14. The prosody-data distributing method according to claim 13, wherein said prosody data is supplied by referring to a management list of the predetermined voice contents which is open to public.

15. The prosody-data distributing method according to claim 12, wherein said supplying of said speech style dictionary to said terminal device further includes selecting a speech style dictionary corresponding to a speech style pointed to by a user'"'"'s terminal-device transferring said selected speech style dictionary to said terminal device from said server, and storing said transferred speech style dictionary into a speech-style-dictionary memory in said terminal device, so that voice synthesis is carried out with said speech style pointed to by said terminal-device user.

16. A prosody-data distributing method according to claim 12, wherein the speech dictionary further includes information of the plurality of stereotypical sentences.