MULTIPLE LANGUAGE VOICE RECOGNITION

• US 20100211376A1
• Filed: 02/02/2010
• Published: 08/19/2010
• Est. Priority Date: 02/17/2009
• Status: Active Grant

• Current Assignee: Sony Interactive Entertainment Inc. (Sony Group Corp.)
• Original Assignee: Sony Computer Entertainment Incorporated (Sony Group Corp.)
• Inventors: Omote, Masanori, Hernandez-Abrego, Gustavo, Chen, Ruxin, Menendez-Pidal, Xavier
• Granted Patent: US 8,788,256 B2
• Time in Patent Office: Days
• US Class Current: 704/2
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

Computer implemented speech processing generates one or more pronunciations of an input word in a first language by a non-native speaker of the first language who is a native speaker of a second language. The input word is converted into one or more pronunciations. Each pronunciation includes one or more phonemes selected from a set of phonemes associated with the second language. Each pronunciation is associated with the input word in an entry in a computer database. Each pronunciation in the database is associated with information identifying a pronunciation language and/or a phoneme language.

Claims

1. A computer speech processing apparatus, comprising:

a memory unit;

a processing unit coupled to the memory unit;

a pronunciation generator configured for execution by the processor, wherein the pronunciation generator is configured to generate one or more pronunciations of an input word in a first language by a non-native speaker of the first language who is a native speaker of a second language, by;

a) converting the input word into one or more pronunciations, wherein each pronunciation includes one or more phonemes selected from a set of phonemes associated with the second language; and

b) associating each pronunciation of the one or more pronunciations with the input word in an entry in a computer database stored in the memory unit; and

c) associating information identifying a pronunciation language and/or a phoneme language with each pronunciation in the database.

2. The apparatus of claim 1, further comprising:

a speech conversion unit configured to convert a sound signal produced by a speaker into a group of input phonemes, wherein the processor is configured to;

compare the group of input phonemes to one or more pronunciations in one or more entries in the database; and

trigger a change of state of the system corresponding to an entry that includes a pronunciation that matches the group of input phonemes.

3. The apparatus of claim 1 wherein a) comprises converting the input word into one or more groups of one or more second language phonemes selected from the set of phonemes associated with the second language.

4. The apparatus of claim 1, wherein a) comprises converting the input word into one or more sets of one or more first language phonemes selected from a set of phonemes associated with the first language and transforming each first language phoneme in the one or more sets of one or more phonemes into one or more corresponding second language phonemes associated with the second language.

5. The apparatus of claim 4, wherein transforming each first language phoneme includes mapping each first language phoneme into a corresponding intermediate phoneme and mapping each intermediate phoneme into a corresponding second language phoneme.

6. The apparatus of claim 1, wherein the pronunciation generator is further configured to determine a consensus from among a plurality of pronunciations for a given word in the database entry, and, based on the consensus, discard redundant, invalid or unlikely pronunciations from the entry.

7. The apparatus of claim 1, wherein a) comprises:

comparing an input word in the first language to one or more entries in a partial database of words in the first language and corresponding pronunciations and wherein b) comprises entering the word and corresponding pronunciation(s) into the database based on a result of the comparison.

8. The apparatus of claim 7 wherein for an input word matching an entry in the partial database having the first language as the phoneme language and the pronunciation language, b) comprises entering the input word and corresponding pronunciation(s) to a database associated with the first language.

9. The apparatus of claim 7, wherein for an input word matching an entry in the partial database having the second language as the phoneme language and the first language as the pronunciation language, b) comprises entering the input word and corresponding pronunciation(s) to a database associated with a hybrid of the first language and second language.

10. The apparatus of claim 7 wherein for an input word not having a pronunciation in the first language a) comprises generating a corresponding pronunciation using one or phonemes selected from a set of phonemes associated with the first language and b) comprises entering the input word and corresponding pronunciation to a database associated with the first language.

11. The apparatus of claim 7, wherein for an input word not having a pronunciation in the second language, a) comprises generating a pronunciation by converting the word to a group of one or more first language phonemes and mapping the one or more first language phonemes to one or more corresponding second language phonemes, and b) comprises entering the input word and corresponding pronunciation(s) to a database associated with a hybrid of the first language and second language.

12. In a computer speech processing apparatus having a processing unit and a memory unit, a computer implemented method for generating one or more pronunciations of an input word in a first language by a non-native speaker of the first language who is a native speaker of a second language, the method comprising:

a) converting the input word into one or more pronunciations with the processing unit, wherein each pronunciation includes one or more phonemes selected from a set of phonemes associated with the second language; and

b) associating each pronunciation of the one or more pronunciations with the input word in an entry in a computer database stored in the memory unit; and

c) associating information identifying a pronunciation language and/or a phoneme language with each pronunciation in the database.

13. The method of claim 12, further comprising:

c) converting a sound signal produced by a speaker into a group of input phonemes;

d) comparing the group of phonemes to one or more entries in the database; and

e) executing a command corresponding to an entry that matches the group of input phonemes.

14. The method of claim 12, wherein a) comprises converting the input word into one or more sets of one or more second language phonemes selected from a set of phonemes associated with the second language.

15. The method of claim 12, wherein a) comprises converting the input word into one or more sets of one or more first language phonemes selected from a set of phonemes associated with the first language and transforming each first language phoneme in the one or more sets of one or more phonemes into one or more corresponding second language phonemes associated with the second language.

16. The method of claim 15, wherein transforming each first language phoneme includes mapping each first language phoneme into a corresponding intermediate phoneme and mapping each intermediate phoneme into a corresponding second language phoneme.

17. The method of claim 12, further comprising determining a consensus from a plurality of pronunciations for a given word in the database entry, and, based on the consensus, discarding redundant, invalid or unlikely pronunciations.

18. The method of claim 12, wherein a) comprises:

comparing an input word in the first language to one or more entries in a partial database of words in the first language and corresponding pronunciations and wherein b) comprises entering the word and corresponding pronunciation(s) into the database based on a result of the comparison.

19. The method of claim 18 wherein for an input word matching an entry in the partial database having the first language as the phoneme language and the pronunciation language, b) comprises entering the input word and corresponding pronunciation(s) to a database associated with the first language.

20. The method of claim 18, wherein for an input word matching an entry in the partial database having the second language as the phoneme language and the first language as the pronunciation language, b) comprises entering the input word and corresponding pronunciation(s) to a database associated with a hybrid of the first language and second language.

21. The method of claim 18 wherein for an input word not having a pronunciation in the first language a) comprises generating a corresponding pronunciation using one or phonemes selected from a set of phonemes associated with the first language and b) comprises entering the input word and corresponding pronunciation to a database associated with the first language.

22. The method of claim 18, wherein for an input word not having a pronunciation in the second language, a) comprises generating a pronunciation by converting the word to a group of one or more first language phonemes and mapping the one or more first language phonemes to one or more corresponding second language phonemes, and b) comprises entering the input word and corresponding pronunciation(s) to a database associated with a hybrid of the first language and second language.

23. A system for implementing computer speech processing in a computer speech processing apparatus having a processing unit and a memory unit, the system comprising:

a) means for converting the input word into one or more pronunciations, wherein each pronunciation includes one or more phonemes selected from a set of phonemes associated with the second language; and

b) means for associating each pronunciation of the one or more pronunciations with the input word in an entry in a computer database stored in the memory unit; and

c) means for associating information identifying a pronunciation language and/or a phoneme language with each pronunciation in the database.

24. A computer readable storage medium, having embodied therein computer readable instructions for implementing computer graphics processing in a computer speech processing apparatus having a processing unit and a memory unit, the instructions comprising:

a) one or more instructions that, when executed by the processor, convert an input word into one or more pronunciations with the processing unit, wherein each pronunciation includes one or more phonemes selected from a set of phonemes associated with the second language; and

b) one or more instructions that, when executed by the processor, associate each pronunciation of the one or more pronunciations with the input word in an entry in a computer database stored in the memory unit; and

c) one or more instructions that, when executed by the processor, associate information identifying a pronunciation language and/or a phoneme language with each pronunciation in the database.