P

Inventor

BAHL LALIT R

US27 patents

Patents

27 patents
US5333236AJul 26, 1994

Speech recognizer having a speech coder for an acoustic match based on context-dependent speech-transition acoustic models

IBM247 citations99
US5195167AMar 16, 1993

Apparatus and method of grouping utterances of a phoneme into context-dependent categories based on sound-similarity for automatic speech recognition

IBM197 citations99
US5165007ANov 17, 1992

Feneme-based Markov models for words

IBM238 citations99
US5033087AJul 16, 1991

Method and apparatus for the automatic determination of phonological rules as for a continuous speech recognition system

IBM302 citations99
US4833712AMay 23, 1989

Automatic generation of simple Markov model stunted baseforms for words in a vocabulary

IBM262 citations99
US4819271AApr 4, 1989

Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments

IBM285 citations99
US5233681AAug 3, 1993

Context-dependent speech recognizer using estimated next word context

IBM82 citations96
US4980918ADec 25, 1990

Speech recognition system with efficient storage and rapid assembly of phonological graphs

IBM115 citations96
US4977599ADec 11, 1990

Speech recognition employing a set of Markov models that includes Markov models representing transitions to and from silence

IBM56 citations96
US4827521AMay 2, 1989

Training of markov models used in a speech recognition system

IBM54 citations96
US4817156AMar 28, 1989

Rapidly training a speech recognizer to a subsequent speaker given training data of a reference speaker

IBM104 citations96
US4741036AApr 26, 1988

Determination of phone weights for markov models in a speech recognition system

IBM65 citations96
US4718094AJan 5, 1988

Speech recognition system

IBM327 citations96
US6343270B1Jan 29, 2002

Method for increasing dialect precision and usability in speech recognition and text-to-speech systems

IBM66 citations95
US4748670AMay 31, 1988

Apparatus and method for determining a likely word sequence from labels generated by an acoustic processor

IBM64 citations95
US4291406ASep 22, 1981

Error correction on burst channels by sequential decoding

IBM69 citations94
US6377921B1Apr 23, 2002

Identifying mismatches between assumed and actual pronunciations of words

IBM35 citations92
US5280562AJan 18, 1994

Speech coding apparatus with single-dimension acoustic prototypes for a speech recognizer

IBM20 citations92
US5278942AJan 11, 1994

Speech coding apparatus having speaker dependent prototypes generated from nonuser reference data

IBM50 citations92
US5182773AJan 26, 1993

Speaker-independent label coding apparatus

IBM35 citations92
US4882759ANov 21, 1989

Synthesizing word baseforms used in speech recognition

IBM40 citations92
US4852173AJul 25, 1989

Design and construction of a binary-tree system for language modelling

IBM43 citations92
US4759068AJul 19, 1988

Constructing Markov models of words from multiple utterances

IBM53 citations92
US5497447AMar 5, 1996

Speech coding apparatus having acoustic prototype vectors generated by tying to elementary models and clustering around reference vectors

IBM43 citations90
US5455889AOct 3, 1995

Labelling speech using context-dependent acoustic prototypes

IBM50 citations87
US5276766AJan 4, 1994

Fast algorithm for deriving acoustic prototypes for automatic speech recognition

IBM17 citations74
US5129001AJul 7, 1992

Method and apparatus for modeling words with multi-arc markov models

IBM18 citations74