David J Roe

US Patent:

57377243, Apr 7, 1998

Filed:

Aug 8, 1996

Appl. No.:

8/695140

Inventors:

Bishnu Saroop Atal - New Providence NJ
Raziel Haimi-Cohen - Springfield NJ
David Bjorn Roe - Berkeley Heights NJ

Assignee:

Lucent Technologies Inc. - Murray Hill NJ

International Classification:

G01L 506

US Classification:

704251

Abstract:

The invention relates to a method and apparatus for speech recognition, the speech to be recognized including one or more words. Recognition is based on an analysis of a first and a second utterance. In accordance with the invention, the first utterance is compared to one or more models of speech to determine a similarity metric for each such comparison. The model of speech which most closely matches the first utterance is determined based on the one or more similarity metrics. The similarity metric corresponding to the most closely matching model of speech is analyzed to determine whether the similarity metric satisfies a first recognition criterion. The second utterance is compared to one or more models of speech associated with the most closely matching model (which may include the most closely matching model) to determine a second utterance similarity metric for each such comparison. The one or more second utterance similarity metrics are analyzed to determine whether the one or more metrics satisfies a second recognition criteria. The second utterance is recognized has the phrase corresponding to the most closely matching model of speech when the first and second recognition criteria are satisfied.

US Patent:

53296087, Jul 12, 1994

Filed:

Aug 18, 1993

Appl. No.:

8/108839

Inventors:

Enrico L. Bocchieri - Madison NJ
Sedat I. Gokcen - Gahanna OH
Rajendra P. Mikkilineni - Gahanna OH
David B. Roe - Berkeley Heights NJ
Jay G. Wilpon - Warren NJ

Assignee:

AT&T Bell Laboratories - Murray Hill NJ

International Classification:

G10L 504

US Classification:

395 252

Abstract:

Apparatus and method for recording data in a speech recognition system and recognizing spoken data corresponding to the recorded data. The apparatus and method responds to entered data by generating a string of phonetic transcriptions from the entered data. The data and generated phonetic transcription string associated therewith is recorded in a vocabulary lexicon of the speech recognition system. The apparatus and method responds to receipt of spoken data by constructing a model of subwords characteristic of the spoken data and compares the constructed subword model with ones of the recorded lexicon vocabulary recorded phonetic transcription strings to recognize the spoken data as the data identified by and associated with a phonetic transcription string matching the constructed subword string.

US Patent:

57377235, Apr 7, 1998

Filed:

Aug 29, 1994

Appl. No.:

8/297283

Inventors:

Michael Dennis Riley - New York NY
David Bjorn Roe - Berkeley Heights NJ

Assignee:

Lucent Technologies Inc. - Murray Hill NJ

International Classification:

G10L 900

US Classification:

704243

Abstract:

A speech recognition system may be trained with data that is independent from previous acoustics. This method of training is quicker and more cost effective than previous training methods. In training the system, after a vocabulary word is input into the system, a first set of phonemes representative of the vocabulary word is determined. Next, the first set of phonemes is compared with a second set of phonemes representative of a second vocabulary word. The first vocabulary word and the second vocabulary word are different. The comparison generates a confusability index. The confusability index for the second word is a measure of the likelihood that the second word will be mistaken as another vocabulary word, e. g. , the first word, already in the system. This process may be repeated for each newly desired vocabulary word.