Pronunciation generation in speech recognition

Details Pronunciation generation in speech recognition Pronunciation generation in speech recognition

1997-03-28

2000-07-18

Zele, Krista

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

G10L 1508

Patent

active

060920440

ABSTRACT:
A method of adding a word to a speech recognition vocabulary includes creating a collection of possible phonetic pronunciations from a spelling of the word and using speech recognition to find a pronunciation from the collection that best matches an utterance of the word. The collection is created by comparing the spelling to a rules list of letter strings with associated phonemes. The list is searched for a letter string from the spelling of length greater than one letter. The collection is limited to phonetic pronunciations containing phonemes associated with the letter string of length greater than one. In another method, a net of possible phonetic pronunciations of the word is created from the spelling and speech recognition is used to find the pronunciation from the net that best matches the utterance of the word. The invention also features methods of assigning a pre-filtering class to a word.

REFERENCES:
patent: 4481593 (1984-11-01), Bahler
patent: 4489435 (1984-12-01), Moshier
patent: 4718094 (1988-01-01), Bahl et al.
patent: 4783803 (1988-11-01), Baker et al.
patent: 4805218 (1989-02-01), Bamberg et al.
patent: 4805219 (1989-02-01), Baker et al.
patent: 4829576 (1989-05-01), Porter
patent: 4833712 (1989-05-01), Bahl et al.
patent: 5027406 (1991-06-01), Roberts et al.
patent: 5208897 (1993-05-01), Hutchins
patent: 5222188 (1993-06-01), Hutchins
patent: 5293451 (1994-03-01), Brown et al.
patent: 5329609 (1994-07-01), Sanada et al.
patent: 5428707 (1995-06-01), Gould et al.
patent: 5440663 (1995-08-01), Moese et al.
patent: 5497447 (1996-03-01), Bahl et al.
patent: 5500920 (1996-03-01), Kupiec
patent: 5623578 (1997-04-01), Mikkilineni
patent: 5652828 (1997-07-01), Silverman
patent: 5748840 (1998-05-01), La Rue
patent: 5751906 (1998-05-01), Silverman
patent: 5765132 (1998-06-01), Roberts
patent: 5794189 (1998-08-01), Gould
patent: 5815639 (1998-09-01), Bennett et al.
patent: 5850627 (1998-12-01), Gould et al.
Kita, Kenji et al., "Processing Unknown Words in Continuous Speech Recognition," IEICE Trans., vol. E74, No. 7 (Jul. 1991), pp. 1811-1815.
Asadi, et al.; "Automatic Modeling for Adding New Words to a Large-Vocabulary Continuous Speech Recognition System"; ICASSP 91 vol. 1; International Conference; pp. 305-308.
Bahl, et al.; "A Maximum Likelihood Approach to Continuous Speech Recognition"; IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5; No. 2, Mar. 1983.
European Search Report dated Apr. 7, 1999.
Asadi, Ayman, "Automatic Modeling for Adding New Words to a Large Vocabulary . . . ", ICASSP 91, vol. 1, pp. 305-308, 1991.
Bahl, Lalit, "A Maximum LikeLihood Approach to Continuous Speech Recognition", IEEE Transactions on Patern Analysis and Machine Intelligence, vol. PAMI-5, No. 2, pp. 179-190, Mar. 1983.
Bahl, L.R., "Automatic High-Resolution Labeling of Speech Waveforms", IBM Technical Disclosure Bulletin, vol. 23, No. 7B, pp. 3466-3467, Dec. 1980.
Bahl, L.R., "Automatic Phonetic Baseform Determination", ICASSP 91, vol. 1, pp. 173-176, May 1991.
Bahl, L.R., "Adaptation of Large Vocabulary Recognition System" ICASSP-92, vol. 1, pp. I477-480 Mar. 1992.
Bahl, L.R., "Automatic Selection of Speech Prototypes " IBM Technical Disclosure Bulletin vol. 24, No. 4, pp. 2042-2043, Sep. 1981.
Bahl, L.R., "Interpolation of Estimators Derived From Sparse Data", IBM Technical Disclosure Bulletin vol. 24, No. 4, pp. 2038-2041, Sep. 1981.
Das, S.K., "System for Temporal Registration of Quasi-Phonemic Utterance Representations", IBM Technical Disclosure Bulletin, Bol. 23, No. 7A, pp. 3047-3050, Dec. 1980.
Haeb-Unbach, R., "Automatic Transcription of Unknown Words in a Speech Recognition System", The 1995 International Conference on Acoustice, Speech, and Signal Processing, vol. 1, pp. 840-843, May 1995.
Hunnicutt, Sheri, "Reversible Letter-to-Sound Sound-to-Letter Generation . . . ", Eurospeech '93, vol. 2, pp. 763-766.
Imai, Toru, "ANew Method for Automatic Generation of Speaker-Dependent Phonological Rules", The 1995 International Conference on Acoustice, Speech, and Signal Processing, vol. 1, pp. 864-867, May 1995.
Merialdo B., "Multilevel decoding for Very-Large-Size-Dictionary speech recognition", IBM J. Res. Develop., vol. 32, No. 2, Mar. 1988.
Wothke, K., "Morphologically based automatic phonetic transcription", IBM Systems Journal, vol. 32, No. 3, 1993.

Affiliated with

Also associated with

Rating

Pronunciation generation 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 Pronunciation generation in speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pronunciation generation in speech recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2047569