Lalit R. Bahl

According to our database, Lalit R. Bahl authored at least 70 papers between 1969 and 1999.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

1999

Partitioning the feature space of a classifier with linear hyperplanes.

Mukund Padmanabhan, Lalit R. Bahl, David Nahamoo

IEEE Trans. Speech Audio Process., 1999

1998

Speaker clustering and transformation for speaker adaptation in speech recognition systems.

Mukund Padmanabhan, Lalit R. Bahl, David Nahamoo, Michael A. Picheny

IEEE Trans. Speech Audio Process., 1998

A time-synchronous, tree-based search strategy in the acoustic fast match of an asynchronous speech recognition system.

Ellen Eide, Lalit R. Bahl

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

A method for modeling liaison in a speech recognition system for French.

Lalit R. Bahl, Steven V. De Gennaro, Pieter de Souza, Edward A. Epstein, J. M. Le Roux, Burn L. Lewis, Claire Waast

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Acoustics-only based automatic phonetic baseform generation.

Bhuvana Ramabhadran, Lalit R. Bahl, Peter DeSouza, Mukund Padmanabhan

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

Speech recognition performance on a voicemail transcription task.

Mukund Padmanabhan, Ellen Eide, Bhuvana Ramabhadran, Ganesh N. Ramaswamy, Lalit R. Bahl

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

A discriminant measure for model complexity adaptation.

Lalit R. Bahl, Mukund Padmanabhan

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

1997

Decision-tree based quantization of the feature space of a speech recognizer.

Mukund Padmanabhan, Lalit R. Bahl, David Nahamoo, Pieter de Souza

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

1996

Speaker clustering and transformation for speaker adaptation in large-vocabulary speech recognition systems.

Mukund Padmanabhan, Lalit R. Bahl, David Nahamoo, Michael A. Picheny

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

Discriminative training of Gaussian mixture models for large vocabulary speech recognition systems.

Lalit R. Bahl, Mukund Padmanabhan, David Nahamoo, P. S. Gopalakrishnan

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

1995

Fast match based on decision tree.

Claire Waast, Lalit R. Bahl, Marc El-Bèze

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

A tree search strategy for large-vocabulary continuous speech recognition.

P. S. Gopalakrishnan, Lalit R. Bahl, Robert L. Mercer

Proceedings of the 1995 International Conference on Acoustics, 1995

Experiments using data augmentation for speaker adaptation.

Jerome R. Bellegarda, Peter V. de Souza, David Nahamoo, Mukund Padmanabhan, Michael A. Picheny, Lalit R. Bahl

Proceedings of the 1995 International Conference on Acoustics, 1995

Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task.

Lalit R. Bahl, S. Balakrishnan-Aiyer, Jerome R. Bellegarda, Martin Franz, P. S. Gopalakrishnan, David Nahamoo, Miroslav Novak, Mukund Padmanabhan, Michael A. Picheny, Salim Roukos

Proceedings of the 1995 International Conference on Acoustics, 1995

1994

The metamorphic algorithm: a speaker mapping approach to data augmentation.

Jerome R. Bellegarda, Peter V. de Souza, Arthur Nádas, David Nahamoo, Michael A. Picheny, Lalit R. Bahl

IEEE Trans. Speech Audio Process., 1994

Robust methods for using context-dependent features and models in a continuous speech recognizer.

Lalit R. Bahl, Peter V. de Souza, Ponani S. Gopalakrishnan, David Nahamoo, Michael A. Picheny

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

1993

A fast approximate acoustic match for large vocabulary speech recognition.

Lalit R. Bahl, Steven V. De Gennaro, P. S. Gopalakrishnan, Robert L. Mercer

IEEE Trans. Speech Audio Process., 1993

A method for the construction of acoustic Markov models for words.

Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer, Michael A. Picheny

IEEE Trans. Speech Audio Process., 1993

Estimating hidden Markov model parameters so as to maximize speech recognition accuracy.

Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer

IEEE Trans. Speech Audio Process., 1993

Multonic Markov word models for large vocabulary continuous speech recognition.

Lalit R. Bahl, Jerome R. Bellegarda, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael A. Picheny

IEEE Trans. Speech Audio Process., 1993

Word lookahead scheme for cross-word right context models in a stack decoder.

Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael Picheny

Proceedings of the Third European Conference on Speech Communication and Technology, 1993

A supervised approach to the construction of context-sensitive acoustic prototypes.

Jerome R. Bellegarda, Peter V. de Souza, David Nahamoo, Michael A. Picheny, Lalit R. Bahl

Proceedings of the IEEE International Conference on Acoustics, 1993

Context dependent vector quantization for continuous speech recognition.

Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, Michael A. Picheny

Proceedings of the IEEE International Conference on Acoustics, 1993

1992

Constructing candidate word lists using acoustically similar word groups.

Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, Dimitri Kanevsky, David Nahamoo

IEEE Trans. Signal Process., 1992

Robust speaker adaptation using a piecewise linear acoustic mapping.

Jerome R. Bellegarda, Peter V. de Souza, Arthur Nádas, David Nahamoo, Michael A. Picheny, Lalit R. Bahl

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

Adaptation of large vocabulary recognition system parameters.

Lalit R. Bahl, Peter V. de Souza, David Nahamoo, Michael A. Picheny, Salim Roukos

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

A fast match for continuous speech recognition using allophonic models.

Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael A. Picheny

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

1991

Context Dependent Modeling of Phones in Continuous Speech Using Decision Trees.

Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael Picheny

Proceedings of the Speech and Natural Language, 1991

A fast algorithm for deleted interpolation.

Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer, David Nahamoo

Proceedings of the Second European Conference on Speech Communication and Technology, 1991

Decision trees for phonological rules in continuous speech.

Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael A. Picheny

Proceedings of the 1991 International Conference on Acoustics, 1991

Automatic phonetic baseform determination.

Lalit R. Bahl, Subrata K. Das, Peter DeSouza, M. Epstein, Robert L. Mercer, Bernard Mérialdo, David Nahamoo, Michael A. Picheny, J. Powell

Proceedings of the 1991 International Conference on Acoustics, 1991

A new class of fenonic Markov word models for large vocabulary continuous speech recognition.

Lalit R. Bahl, Jerome R. Bellegarda, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael A. Picheny

Proceedings of the 1991 International Conference on Acoustics, 1991

1990

Constructing groups of acoustically confusable words.

Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, Dimitri Kanevsky, David Nahamoo

Proceedings of the 1990 International Conference on Acoustics, 1990

1989

A tree-based statistical language model for natural language speech recognition.

Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer

IEEE Trans. Acoust. Speech Signal Process., 1989

Matrix fast match: a fast method for identifying a short list of candidate words for decoding.

Lalit R. Bahl, P. S. Gopalakrishnan, Dimitri Kanevsky, David Nahamoo

Proceedings of the IEEE International Conference on Acoustics, 1989

Large vocabulary natural language continuous speech recognition.

Lalit R. Bahl, Raimo Bakis, Jerome R. Bellegarda, Peter F. Brown, David Burshtein, Subrata K. Das, Peter V. de Souza, P. S. Gopalakrishnan, Frederick Jelinek, Dimitri Kanevsky, Robert L. Mercer, Arthur Nádas, David Nahamoo, Michael A. Picheny

Proceedings of the IEEE International Conference on Acoustics, 1989

1988

Acoustic Markov models used in the Tangora speech recognition system.

Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer, Michael A. Picheny

Proceedings of the IEEE International Conference on Acoustics, 1988

A new algorithm for the estimation of hidden Markov model parameters.

Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1988

Obtaining candidate words by polling in a large vocabulary speech recognition system.

Lalit R. Bahl, Raimo Bakis, Peter V. de Souza, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1988

Speech recognition with continuous-parameter hidden Markov models.

Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1988

1987

Experiments with the Tangora 20, 000 word speech recognizer.

Amir Averbuch, Lalit R. Bahl, Raimo Bakis, Peter F. Brown, G. Daggett, S. Das, Ken Davies, Steven V. De Gennaro, Peter V. de Souza, E. Epstein, D. Fraleigh, Frederick Jelinek, B. Lewis, Robert L. Mercer, J. Moorhead, Arthur Nádas, David Nahamoo, Michael Picheny, G. Shichman, P. Spinelli, Dirk Van Compernolle, H. Wilkens

Proceedings of the IEEE International Conference on Acoustics, 1987

1986

Maximum mutual information estimation of hidden Markov model parameters for speech recognition.

Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1986

An IBM PC based large-vocabulary isolated-utterance speech recognizer.

Amir Averbuch, Lalit R. Bahl, Raimo Bakis, Peter F. Brown, A. G. Cole, G. Daggett, Subrata K. Das, Ken Davies, S. DeGennaro, Peter V. de Souza, E. Epstein, D. Fraleigh, Frederick Jelinek, Slava M. Katz, B. Lewis, Robert L. Mercer, Arthur Nádas, David Nahamoo, Michael Picheny, G. Shichman, P. Spinelli

Proceedings of the IEEE International Conference on Acoustics, 1986

1984

Some experiments with large-vocabulary isolated-word sentence recognition.

Lalit R. Bahl, Subrata K. Das, Peter V. de Souza, Frederick Jelinek, Slava M. Katz, Robert L. Mercer, Michael A. Picheny

Proceedings of the IEEE International Conference on Acoustics, 1984

1983

A Maximum Likelihood Approach to Continuous Speech Recognition.

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer

IEEE Trans. Pattern Anal. Mach. Intell., 1983

Recognition of isolated-word sentences from a 5000-word vocabulary office correspondence task.

Lalit R. Bahl, A. G. Cole, Frederick Jelinek, Robert L. Mercer, Arthur Nádas, David Nahamoo, Michael Picheny

Proceedings of the IEEE International Conference on Acoustics, 1983

1982

25 Continuous speech recognition: Statistical methods.

Frederick Jelinek, Robert L. Mercer, Lalit R. Bahl

Proceedings of the Classification, Pattern Recognition and Reduction of Dimensionality, 1982

1981

Continuous speech recognition with automatically selected acoustic prototypes obtained by either bootstrapping or clustering.

Arthur Nádas, Robert L. Mercer, Lalit R. Bahl, Raimo Bakis, Paul S. Cohen, A. G. Cole, Frederick Jelinek, Burn L. Lewis

Proceedings of the IEEE International Conference on Acoustics, 1981

Speech recognition of a natural text read as isolated words.

Lalit R. Bahl, Raimo Bakis, Paul S. Cohen, A. G. Cole, Frederick Jelinek, Burn L. Lewis, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1981

Continuous parameter acoustic processing for recognition of a natural speech corpus.

Lalit R. Bahl, Raimo Bakis, Paul S. Cohen, A. G. Cole, Frederick Jelinek, Burn L. Lewis, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1981

1980

Further results on the recognition of a continuously read natural corpus.

Lalit R. Bahl, Raimo Bakis, Paul S. Cohen, A. G. Cole, Frederick Jelinek, Burn L. Lewis, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1980

1979

Recognition results for several experimental acoustic processors.

Lalit R. Bahl, Raimo Bakis, Paul S. Cohen, A. G. Cole, Frederick Jelinek, Burn L. Lewis, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1979

1978

Optimization of Teleprocessing Networks with Concentrators and Multiconnected Terminals.

Donald T. Tang, Lin S. Woo, Lalit R. Bahl

IEEE Trans. Computers, 1978

Recognition of continuously read natural corpus.

Lalit R. Bahl, James K. Baker, Paul S. Cohen, Frederick Jelinek, Burn L. Lewis, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1978

Automatic recognition of continuously spoken sentences from a finite state grammer.

Lalit R. Bahl, James K. Baker, Paul S. Cohen, A. G. Cole, Frederick Jelinek, Burn L. Lewis, Robert L. Mercer

Proceedings of the IEEE International Conference on Acoustics, 1978

1976

Preliminary results on the performance of a system for the automatic recognition of continuous speech.

Lalit R. Bahl, James K. Baker, Paul S. Cohen, N. R. Dixon, Frederick Jelinek, Robert L. Mercer, Harvey F. Silverman

Proceedings of the IEEE International Conference on Acoustics, 1976

1975

Design of a linguistic statistical decoder for the recognition of continuous speech.

Frederick Jelinek, Lalit R. Bahl, Robert L. Mercer

IEEE Trans. Inf. Theory, 1975

Decoding for channels with insertions, deletions, and substitutions with applications to speech recognition.

Lalit R. Bahl, Frederick Jelinek

IEEE Trans. Inf. Theory, 1975

1974

Optimal decoding of linear codes for minimizing symbol error rate (Corresp.).

Lalit R. Bahl, John Cocke, Frederick Jelinek, Josef Raviv

IEEE Trans. Inf. Theory, 1974

Image Data Compression by Predictive Coding II: Encoding Algorithms.

Hisashi Kobayashi, Lalit R. Bahl

IBM J. Res. Dev., 1974

Image Data Compression by Predictive Coding I: Prediction Algorithms.

Hisashi Kobayashi, Lalit R. Bahl

IBM J. Res. Dev., 1974

1972

On the structure of rate 1/n convolutional codes.

Lalit R. Bahl, Frederick Jelinek

IEEE Trans. Inf. Theory, 1972

An efficient algorithm for computing free distance (Corresp.).

Lalit R. Bahl, C. Cullum, W. Donald Frazer, Frederick Jelinek

IEEE Trans. Inf. Theory, 1972

1971

Rate 1/2 convolutional codes with complementary generators.

Lalit R. Bahl, Frederick Jelinek

IEEE Trans. Inf. Theory, 1971

Single- and multiple-burst-correcting properties of a class of cyclic product codes.

Lalit R. Bahl, Robert T. Chien

IEEE Trans. Inf. Theory, 1971

1970

Block Codes for a Class of Constrained Noiseless Channels

Donald T. Tang, Lalit R. Bahl

Inf. Control., December, 1970

1969

Multiple-Burst-Error Correction by Threshold Decoding

Lalit R. Bahl, Robert T. Chien

Inf. Control., November, 1969

Correction of Single and Multiple Bursts of Errors

Lalit R. Bahl

PhD thesis, 1969

Correction of two erasure bursts (Corresp.).

Robert T. Chien, Lalit R. Bahl, Donald T. Tang

IEEE Trans. Inf. Theory, 1969

On Gilbert burst-error-correcting codes (Corresp.).

Lalit R. Bahl, Robert T. Chien

IEEE Trans. Inf. Theory, 1969