METHOD AND APPARATUS FOR GENERATING MULTILINGUAL TRANSCRIPTION GROUPS

• US 20020173945A1
• Filed: 11/02/1999
• Published: 11/21/2002
• Est. Priority Date: 11/02/1999
• Status: Active Grant

• Current Assignee: RPX Clearinghouse LLC (RPX Corporation)
• Original Assignee: Nortel Networks Limited (Nortel Networks Corporation)
• Inventors: FABIANI, MARC A, SABOURIN, MICHAEL G
• Granted Patent: US 6,549,883 B2
• Time in Patent Office: Days
• US Class Current: 704/1
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

The invention relates to a method and apparatus for generating transcriptions suitable for use in a speech-processing device. The invention provides processing the vocabulary item to derive a characteristic from the vocabulary item allowing to divide a pool of available languages in a first sub-group and a second sub-group. The vocabulary item manifests a higher probability of belonging to any one of the languages in the first sub-group than belonging to any language in the second sub-group. The invention further provides processing the vocabulary item to generate a group of transcriptions, the group of transcriptions being characterized by the absence of at least one transcription belonging to a language in the second sub-group of languages established for the vocabulary item. The group of transcriptions is then released for use by a speech-processing device.

Claims

1. ) A computer readable storage medium comprising a data structure containing a speech recognition dictionary suitable for use in a speech recognizer, said speech recognition dictionary comprising a set of vocabulary items, the set of vocabulary items including a sub-set of vocabulary items, each vocabulary item in the sub-set being associated to a group of transcriptions belonging to languages selected from a pool of available languages, each vocabulary item in said sub-set of vocabulary items having characteristics allowing to divide the pool of available languages in a first sub-group and a second sub-group, the vocabulary item manifesting a higher probability of belonging to any one of the languages in the first sub-group than belonging to any language in the second sub-group, the group of transcriptions associated with each vocabulary item from the sub-set of vocabulary items being characterized by the absence of at least one transcription belonging to a language in the second sub-group of languages established for the vocabulary item.

2. ) A computer readable storage medium as defined in claim 1, wherein the group of transcriptions associated with each vocabulary item from the sub-set of vocabulary items being characterized by the absence of a transcription belonging to any one of the languages in the second sub-group of languages established for the vocabulary item.

3. ) A computer readable storage medium as defined in claim 1, wherein each vocabulary item in said sub-set are associated to transcriptions belonging to a common default language.

4. ) A computer readable storage medium as defined in claim 1, wherein the vocabulary item is characterized by a certain etymology, wherein a characteristic of the vocabulary item allowing dividing the pool of available languages in the first sub-set and the second sub-set is the etymology of the vocabulary item.

5. ) A computer readable storage medium as defined in claim 4, wherein said vocabulary item is an orthography.

6. ) A method for generating a group of transcriptions suitable for use in a speech processing device, said method comprising:

providing a vocabulary item;

processing the vocabulary item to derive a characteristic from said vocabulary item allowing to divide a pool of available languages in a first sub-group and a second sub-group, the vocabulary item manifesting a higher probability of belonging to any one of the languages in the first sub-group than belonging to any language in the second sub-group;

processing the vocabulary item to generate a group of transcriptions, the group of transcriptions being characterized by the absence of at least one transcription belonging to a language in the second sub-group of languages established for the vocabulary item;

storing the group of transcriptions in a format suitable for use by a speech processing device.

7. ) A method as defined in claim 6, further comprising processing the vocabulary item to generate a transcription corresponding to each language in the first sub-group.

8. ) A method as defined in claim 6, wherein the group of transcriptions is characterized by the absence of a transcriptions belonging to any one of the languages in the second sub-group of languages established for the vocabulary item.

9. ) A method as defined in claim 8, said method further comprising processing all vocabulary items in said sub-set to generate for each vocabulary item in said sub-set a transcription belonging to a common default language.

10. ) A method as defined in claim 9, wherein the vocabulary item is characterized by a certain etymology, a characteristic allowing to divide the pool of available languages in the first sub-group and the second sub-group is the etymology of the vocabulary item.

11. ) A computer readable medium containing a speech recognition dictionary comprising transcriptions generated by the method defined in claim 6.

13. ) An apparatus as defined in claim 12, wherein said speech processing device is a voice synthesizer.

14. ) An apparatus as defined in claim 12, said apparatus comprising:

a processor;

a computer readable storage medium coupled to said processor, said computer readable storage medium comprising a program element for execution by said processor for implementing said processing unit.

15. ) An apparatus as defined in claim 12, said processing unit comprising:

a language of origin determination unit for processing the vocabulary item to derive a characteristic from said vocabulary item allowing to divide the pool of available languages in the first sub-group and the second sub-group;

a multi-lingual automatic transcription generator coupled to said language of origin determination unit for processing the vocabulary item to generate the group of transcriptions.

16. ) An apparatus as defined in claim 12, wherein said processing unit is operative for processing the vocabulary item to generate a group of transcriptions corresponding to languages in the pool of available languages, the group of transcriptions being characterized by the absence of a transcriptions from any one of the languages in the second sub-group of languages established for the vocabulary item.

17. ) An apparatus as defined in claim 12, wherein the vocabulary item is characterized by a certain etymology, the characteristic allowing to divide the pool of available languages in the first sub-group and the second sub-group is the etymology of the vocabulary item.

18. ) An apparatus as defined in claim 15, further comprising a sub-transcription mapping unit operative to map at least one sub-transcription unit in a transcription, said sub-transcription unit belonging to a first language to a sub-transcription unit belonging to a second language.

12. ) An apparatus for generating a group of transcriptions suitable for use in a speech processing device, said apparatus comprising:

an input for receiving signal conveying data representative of a vocabulary item;

a processing unit coupled to said input, said processing unit being operative for;

(a) processing the vocabulary item to derive a characteristic from said vocabulary item allowing to divide a pool of available languages in a first sub-group and a second sub-group, the vocabulary item manifesting a higher probability of belonging to any one of the languages in the first sub-group than belonging to any language in the second sub-group;

(b) processing the vocabulary item to generate a group of transcriptions, the group of transcriptions being characterized by the absence of at least one transcription belonging to a language in the second sub-group of languages established for the vocabulary item;

an output coupled to said processing unit for releasing a signal representative of the group of transcriptions.

19. ) A computer readable storage medium comprising a program element suitable for execution by a computing apparatus for generating a group of transcriptions, said computing apparatus comprising:

a memory unit for storing an electronic representation of a vocabulary item;

a processor operatively connected to said memory unit, said program element when executing on said processor being operative for;

(a) processing the vocabulary item to derive a characteristic from said vocabulary item allowing to divide a pool of available languages in a first sub-group and a second sub-group, the vocabulary item manifesting a higher probability of belonging to any one of the languages in the first sub-group than belonging to any language in the second sub-group;

(b) processing the vocabulary item to generate a group of transcriptions, the group of transcriptions being characterized by the absence of at least one transcription belonging to a language in the second sub-group of languages established for the vocabulary item;

(c) releasing an electronic representation of the group of transcriptions in a format suitable for use by a speech processing device.

20. ) An apparatus for generating a group of transcriptions suitable for use in a speech processing device, said apparatus comprising:

means for receiving data elements representative of a vocabulary item;

means for processing the vocabulary item to derive a characteristic from said vocabulary item allowing to divide a pool of available languages in a first sub-group and a second sub-group, the vocabulary item manifesting a higher probability of belonging to any one of the languages in the first sub-group than belonging to any language in the second sub-group;

means for processing the vocabulary item to generate a group of transcriptions, the group of transcriptions being characterized by the absence of at least one transcription belonging to a language in the second sub-group of languages established for the vocabulary item;

means for releasing the group of transcriptions in a format suitable for use by a speech processing device.