Training and using pronunciation guessers in speech recognition

Details Training and using pronunciation guessers in speech recognition Training and using pronunciation guessers in speech recognition

2003-10-10

2008-12-16

Hudspeth, David R. (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Synthesis

C704S235000, C704S243000

Reexamination Certificate

active

07467087

ABSTRACT:
The error rate of a pronunciation guesser that guesses the phonetic spelling of words used in speech recognition is improved by causing its training to weigh letter-to-phoneme mappings used as data in such training as a function of the frequency of the words in which such mappings occur. Preferably the ratio of the weight to word frequency increases as word frequencies decreases. Acoustic phoneme models for use in speech recognition with phonetic spellings generated by a pronunciation guesser that makes errors are trained against word models whose phonetic spellings have been generated by a pronunciation guesser that makes similar errors. As a result, the acoustic models represent blends of phoneme sounds that reflect the spelling errors made by the pronunciation guessers. Speech recognition enabled systems are made by storing in them both a pronunciation guesser and a corresponding set of such blended acoustic models.

REFERENCES:
patent: 5715367 (1998-02-01), Gillick et al.
patent: 5991364 (1999-11-01), McAllister et al.
patent: 6029132 (2000-02-01), Kuhn et al.
patent: 6230131 (2001-05-01), Kuhn et al.
patent: 6260012 (2001-07-01), Park
patent: 6411932 (2002-06-01), Molnar et al.
patent: 6744861 (2004-06-01), Pershan et al.
Viikki et al., “Speaker and Language -Independent Speech Recognition in Mobile Communication Systems”, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2001.
“Sensory Introduces Voice Recognition S/W Solution for Embedded DSPs”, http://www.sensoryinc.com/html/company/pr99—7.html, Aug. 1999.
Issues in Building General Letter to Sound Rules, by Alan Black, Kevin Lenzo, and Vincent Pagel 1998.
Weighted Entropy Training for Decision Tree Based Text-To-Phoneme Mapping, by Jilei Tian, Janne Suontausta, and Juha Hakkinen, 2003.
Decision Tree Based Text-To-Phoneme Mapping for Speech Recognition, by Janne Suontausta and Juha Hakkinen 2000.
Statement By Edward Porter Regarding Possible Prior Art of May 20, 2008.

Affiliated with

Also associated with

Rating

Training and using pronunciation guessers in speech recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Training and using pronunciation guessers in speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Training and using pronunciation guessers in speech recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4044613