Method and apparatus for style control in natural language generation

• US 6,374,224 B1
• Filed: 03/10/1999
• Issued: 04/16/2002
• Est. Priority Date: 03/10/1999
• Status: Expired due to Term

• Current Assignee: Sony Electronics Inc. (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.), Sony Electronics Inc. (Sony Group Corp.)
• Inventors: Franz, Alexander M., Horiguchi, Keiko
• Primary Examiner(s): Korzuch, William
• Assistant Examiner(s): Lerner, Martin
• Application Number:
  US09/266,248
• Time in Patent Office: 1,133 Days
• Field of Search: 704/3, 704/4, 704/277, 704/261, 704/268, 704/269, 704/266, 379/88.05, 379/88.06
• US Class Current: 704/266
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method and an apparatus for style control in natural language recognition and generation are provided, wherein an acoustic input is received comprising at least one source language. The acoustic input comprises words, sentences, and phrases in a natural spoken language. Source expressions are recognized in the source language. Style parameters are determined for the source expression. The style parameters may be extracted from the source expression, set by the user, or randomly selected by the natural language system. A recognized source expression is selected and confirmed by a user through a user interface. The recognized source expressions are translated from the source language to a target language. An acoustic output is generated from the translated target language source expressions using the style parameters. The style parameters comprise variations selected from a group comprising formality, local dialect, gender, and age variations.

Claims

1. A method for performing style control in language translation, comprising:

receiving acoustic signals comprising at least one source language;

recognizing at least one source expression of the at least one source language;

extracting at least one style parameter from the at least one source expression;

translating the recognized at least one source expression from the at least one source language to at least one target language;

incorporating the at least one style parameter with rule based speech generation to generate at least one acoustic output from the translated at least one target language using the at least one style parameter; and

providing the at least one acoustic output.

2. The method of claim 1, wherein generating at least one acoustic output comprises incorporating the at least one style parameter with rule-based speech generation, wherein the at least one style parameter is consulted during rule-based based generation of the at least one acoustic output.

3. The method of claim 1, wherein the at least one style parameter is extracted from at least one part of a sentence structure selected from a group comprising conjugations, predicate forms, modals, and lexical selections.

4. The method of claim 1, further compressing providing the at least one style parameter as a global parameter.

5. The method of claim 1, wherein the at least one style parameter is selected from a group compressing formality, local dialect, gender, and age variations.

6. A method for performing style control in language translation, comprising:

receiving acoustic signals comprising at least one source language;

recognizing at least one source expression of the at least one source language;

determining at least one style parameter of the at least one source expression by randomly selecting the at least one style parameter;

translating the recognized at least one source expression from the at least one source language to at least one target language;

generating at least one acoustic output from the translated at least one target language using the at least one style parameter; and

providing the at least one acoustic output.

7. An apparatus for spoken language translation comprising:

at least one processor;

an input coupled to the at least one processor, the input capable of receiving acoustic signals comprising at least one source language, the at least one processor configured to translate the received acoustic signals by,

recognizing at least one source expression of the at least one source language;

extracting at least one style parameter from the at least one source expression;

translating the recognized at least one source expression from the at least one source language to at least one target language;

incorporating the at least one style parameter with rule based speech generation to generate at least one acoustic output from the translated at least one target language using the at least one style parameter; and

an output coupled to the at least one processor, the output capable of providing the at least one acoustic output.

8. The apparatus of claim 7, wherein generating at least one acoustic output comprises incorporating the at least one style parameter with rule-based speech generation, wherein the at least one style parameter is consulted during rule-based generation of the at least one acoustic output.

9. An apparatus for spoken language translation comprising:

at least one processor;

an input coupled to the at least one processor, the input capable of receiving acoustic signals comprising at least one source language, the at least one processor configured to translate the received acoustic signals by,

recognizing at least one source expression of the at least one source language;

determining at least one style parameter of the at least one source expression by randomly selecting the at least one style parameter;

translating the recognized at least one source expression from the at least one source language to at least one target language;

generating at least one acoustic output from the translated at least one target language using the at least one style parameter; and

an output coupled to the at least one processor, the output capable of providing the at least one acoustic output.

10. The apparatus of claim 9, wherein the at least one processor is further configured to translate the received acoustic signals by providing the at least one style parameter as a global parameter.

11. The apparatus of claim 9, wherein the at least one style parameter is selected from a group comprising formality, local dialect, gender, and age variations.

12. A computer readable medium containing executable instructions which, when executed in a processing system, causes the system to perform a method for spoken language translation, the method comprising:

receiving acoustic signals comprising at least one source language;

recognizing at least one source expression of the at least one source language;

extracting at least one style parameter from the at least one source expression;

translating the recognized at least one source expression from the at least one source language to at least one target language;

incorporating the at least one style parameter with rule based speech generation to generate at least one acoustic output from the translated at least one target language using the at least one style parameter; and

providing the at least one acoustic output.

13. The computer readable medium of claim 12, wherein generating at least one acoustic output comprises incorporating the at least one style parameter with rule-based speech generation, wherein the at least one style parameter is consulted during rule-based generation of the at least one acoustic output.

14. The computer readable medium of claim 12, wherein the at least one style parameter is extracted from at least one part of a sentence structure selected from a group comprising conjugations, predicate forms, modals, and lexical selections.

15. A computer readable medium containing executable instructions which, when executed in a processing system, causes the system to perform a method for spoken language translation, the method comprising:

receiving acoustic signals comprising at least one source language;

recognizing at least one source expression of the at least one source language;

determining at least one style parameter of the at least one source expression by randomly selecting the at least one style parameter;

translating the recognized at least one source expression from the at least one source language to at least one target language;

generating at least one acoustic output from the translated at least one target language using the at least one style parameter; and

providing the at least one acoustic output.

16. The computer readable medium of claim 15, wherein the method further comprises providing the at least one style parameter as a global parameter.

17. The computer readable medium of claim 15, wherein the at least one style parameter is selected from a group comprising formality, local dialect, gender, and age variations.

18. A language translation system, comprising:

a means for receiving acoustic signals comprising at least one source language;

a means for recognizing at least one source expression of the at least one source language;

a means for extracting at least one style parameter from the at least one source expression;

a means for translating the recognized at least one source expression from the at least one source language to at least one target language;

a means for generating at least one acoustic output from the translated at least one target language using the at least one style parameter; and

a means for providing the at least one acoustic output.

19. The system of claim 18, wherein the means for generating at least one acoustic output comprises a means for incorporating the at least one style parameter with rule-based speech generation, wherein the at least one style parameter is consulted during rule-based generation of the at least one acoustic output.

20. The system of claim 18, wherein the means for determining at least one style parameter comprises a means for extracting the at least one style parameter from the at least one source expression, wherein the at least one style parameter is extracted from at least one part of a sentence structure selected from a group comprising conjugations, predicate forms, modals, and lexical selections.

21. A language translation system, comprising:

a means for receiving acoustic signals comprising at least one source language;

a means for recognizing at least one source expression of the at least one source language;

a means for determining at least one style parameter of the at least one source expression by randomly selecting the at least one style parameter;

a means for translating the recognized at least one source expression fro one source language to at least one target language;

a means for generating at least one acoustic output from the translated at least one target language using the at least one style parameter; and

a means for providing the at least one acoustic output.