Lalit R. Bahl

发表

A Maximum Likelihood Approach to Continuous Speech Recognition

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Système de conception et de construction d'un arbre binaire pour la modélisation du language

Lalit R. Bahl, Peter F. Brown, Peter Vincent Desouza, 1988 .

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

John Cocke, Lalit R. Bahl, Frederick Jelinek, 1974, IEEE Trans. Inf. Theory.

A method for the construction of acoustic Markov models for words

Michael Picheny, Lalit R. Bahl, Robert L. Mercer, 1993, IEEE Trans. Speech Audio Process..

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

Lalit R. Bahl, Mukund Padmanabhan, David Nahamoo, 1997, EUROSPEECH.

Fast match based on decision tree

Lalit R. Bahl, Marc El-Bèze, Claire Waast-Richard, 1995, EUROSPEECH.

Design and construction of a binary decision tree system for language modeling.

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1988 .

Experiments using data augmentation for speaker adaptation

Michael Picheny, Jerome R. Bellegarda, Lalit R. Bahl, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

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

Lalit R. Bahl, Robert L. Mercer, Raimo Bakis, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

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

Lalit R. Bahl, Frederick Jelinek, F. Jelinek, 1975, IEEE Trans. Inf. Theory.

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

Michael Picheny, Lalit R. Bahl, Mukund Padmanabhan, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

Device and method for recognizing voice

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1992 .

A tree search strategy for large-vocabulary continuous speech recognition

Lalit R. Bahl, Robert L. Mercer, Ponani S. Gopalakrishnan, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

A fast admissible method for identifying a short list of candidate words

Lalit R. Bahl, Ponani S. Gopalakrishnan, David Nahamoo, 1992 .

Block Codes for a Class of Constrained Noiseless Channels

Lalit R. Bahl, Donald T. Tang, L. Bahl, 1970, Inf. Control..

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

Lalit R. Bahl, Robert T. Chien, L. Bahl, 1969, IEEE Trans. Inf. Theory.

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

Lalit R. Bahl, Burn L. Lewis, Edward A. Epstein, 1998, ICSLP.

An efficient algorithm for computing free distance (Corresp.)

Lalit R. Bahl, Frederick Jelinek, C. Cullum, 1972, IEEE Trans. Inf. Theory.

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

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

TRANSCRIPTION OF NEW SPEAKING STYLES - VOICEMAIL

Bhuvana Ramabhadran, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1998 .

Decision-tree based feature-space quantization for fast Gaussian computation

Michael Picheny, Ea-Ee Jan, Lalit R. Bahl, 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

A fast match for continuous speech recognition using allophonic models

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1993, IEEE Trans. Speech Audio Process..

Voice coding device and method therefor

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1994 .

Method and apparatus for speech recognition with effective storage and fast zusammenfuegen of phonological representations.

Lalit R. Bahl, Robert L. Mercer, Paul S. Cohen, 1986 .

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

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

Procédé et dispositif pour déterminer une suite probable de mots à partir d'étiquettes produites par un processeur acoustique

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1986 .

Automatic recognition of continuously spoken sentences from a finite state grammer

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1978, ICASSP.

Some experiments with large-vocabulary isolated-word sentence recognition

Michael Picheny, Lalit R. Bahl, Frederick Jelinek, 1984, ICASSP.

Rate 1/2 convolutional codes with complementary generators

Lalit R. Bahl, Frederick Jelinek, F. Jelinek, 1971, IEEE Trans. Inf. Theory.

Correction of two erasure bursts (Corresp.)

Lalit R. Bahl, Robert T. Chien, Donald T. Tang, 1969, IEEE Trans. Inf. Theory.

On the structure of rate 1/n convolutional codes

Lalit R. Bahl, Frederick Jelinek, 1972, IEEE Trans. Inf. Theory.

Acoustic Markov models used in the Tangora speech recognition system

Michael Picheny, Lalit R. Bahl, Robert L. Mercer, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

Continuous parameter acoustic processing for recognition of a natural speech corpus

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1981, ICASSP.

Further results on the recognition of a continuously read natural corpus

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1980, ICASSP.

Adaptation of large vocabulary recognition system parameters

Michael Picheny, Lalit R. Bahl, David Nahamoo, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1975, IEEE Trans. Inf. Theory.

Method and device for the automatic determination of phonological rules for a system for continuous speech recognition.

Lalit R. Bahl, Peter F. Brown, Peter Vincent Desouza, 1990 .

Method for constructing markov model word base form

Michael Picheny, Lalit R. Bahl, Robert L. Mercer, 1988 .

Acoustics-only based automatic phonetic baseform generation

Bhuvana Ramabhadran, Lalit R. Bahl, Mukund Padmanabhan, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Speech recognition with continuous-parameter hidden Markov models

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1987 .

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

Michael Picheny, Jerome R. Bellegarda, Lalit R. Bahl, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1993, EUROSPEECH.

Method and apparatus to produce a Markov model reference patterns of words.

Michael Picheny, Lalit R. Bahl, Robert L. Mercer, 1988 .

A fast algorithm for deleted interpolation

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1991, EUROSPEECH.

A method for speech recognition.

Lalit R. Bahl, Robert L. Mercer, Peter Vincent Desouza, 1986 .

Image Data Compression by Predictive Coding II: Encoding Algorithms

Hisashi Kobayashi, Lalit R. Bahl, 1974, IBM J. Res. Dev..

Large vocabulary natural language continuous speech recognition

Michael Picheny, Jerome R. Bellegarda, Dimitri Kanevsky, 1989, International Conference on Acoustics, Speech, and Signal Processing,.

Fast adaptation of a speech to a new speaker on the basis of data of a reference speaker.

Lalit R. Bahl, Robert L. Mercer, David Nahamoo, 1988 .

A fast approximate acoustic match for large vocabulary speech recognition

Lalit R. Bahl, Robert L. Mercer, Ponani S. Gopalakrishnan, 1989, IEEE Trans. Speech Audio Process..

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

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1989, IEEE Trans. Acoust. Speech Signal Process..

A Maximum Likelihood Approach to Continuous Speech Recognition

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Context Dependent Modeling of Phones in Continuous Speech Using Decision Trees

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1991, HLT.

Robust speaker adaptation using a piecewise linear acoustic mapping

Michael Picheny, Lalit R. Bahl, David Nahamoo, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Speech recognition with continuous-parameter hidden Markov models

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1987, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

Correction of a reported result

Lalit R. Bahl, Frederick Jelinek, J. Baker, 1979 .

Constructing groups of acoustically confusable words

Dimitri Kanevsky, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1990, International Conference on Acoustics, Speech, and Signal Processing.

Recognition of continuously read natural corpus

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1978, ICASSP.

The metamorphic algorithm: a speaker mapping approach to data augmentation

Michael Picheny, Jerome R. Bellegarda, Lalit R. Bahl, 1994, IEEE Trans. Speech Audio Process..

Constructing candidate word lists using acoustically similar word groups

Dimitri Kanevsky, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1992, IEEE Trans. Signal Process..

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

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Partitioning the feature space of a classifier with linear hyperplanes

Lalit R. Bahl, Mukund Padmanabhan, David Nahamoo, 1999, IEEE Trans. Speech Audio Process..

Procédé pour produire des modèles de mots à partir de plusieurs prononciations pour la reconnaissance de la parole

Michael Picheny, Lalit R. Bahl, Robert L. Mercer, 1986 .

Multonic Markov word models for large vocabulary continuous speech recognition

Michael Picheny, Jerome R. Bellegarda, Lalit R. Bahl, 1993, IEEE Trans. Speech Audio Process..

Voice recognition device and label generation method

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1994 .

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

Michael Picheny, Lalit R. Bahl, Frederick Jelinek, 1983, ICASSP.

Speech recognition of a natural text read as isolated words

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1981, ICASSP.

AUTOMATIC PHONETIC BASEFORM DETERMINATION s3.5

Michael Picheny, Lalit R. Bahl, Robert L. Mercer, 1991 .

A new algorithm for the estimation of hidden Markov model parameters

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

A discriminant measure for model complexity adaptation

Lalit R. Bahl, Mukund Padmanabhan, L. Bahl, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Decision trees for phonological rules in continuous speech

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

Multiple-Burst-Error Correction by Threshold Decoding

Lalit R. Bahl, Robert T. Chien, L. Bahl, 1969, Inf. Control..

Procédé et dispositif de reconnaissance de la parole utilisant des représentations statistiques des mots

Lalit R. Bahl, Robert L. Mercer, Peter Vincent Desouza, 1986 .

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

Amir Averbuch, Lalit R. Bahl, Robert L. Mercer, 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Image Data Compression by Predictive Coding I: Prediction Algorithms

Hisashi Kobayashi, Lalit R. Bahl, 1974, IBM J. Res. Dev..

Automatic construction of acoustic markov models for words

Lalit R. Bahl, Robert L. Mercer, Peter F. Brown, 1987 .

A method and apparatus for predicting the signal level value of a message element

Lalit R. Bahl, Hisashi Kobayashi, David D Grossman, 1973 .

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

Dimitri Kanevsky, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1989, International Conference on Acoustics, Speech, and Signal Processing,.

Context dependent vector quantization for continuous speech recognition

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

Lalit R. Bahl, Robert T. Chien, L. Bahl, 1971, IEEE Trans. Inf. Theory.

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

Lalit R. Bahl, Ellen Eide, 1998, ICSLP.

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

Michael Picheny, Jerome R. Bellegarda, Lalit R. Bahl, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

Speaker clustering and transformation for speaker adaptation in speech recognition systems

Michael Picheny, Lalit R. Bahl, Mukund Padmanabhan, 1998, IEEE Trans. Speech Audio Process..

Experiments with the Tangora 20,000 word speech recognizer

Lalit R. Bahl, Robert L. Mercer, David Nahamoo, 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Automatic phonetic baseform determination

Michael Picheny, Lalit R. Bahl, Robert L. Mercer, 1990 .

Optimization of Teleprocessing Networks with Concentrators and Multiconnected Terminals

Lalit R. Bahl, Donald T. Tang, Lin S. Woo, 1978, IEEE Transactions on Computers.

outputting speech recognizer with speech, the ranks of acoustic prototypes.

Michael Picheny, Lalit R. Bahl, Ponani S. Gopalakrishnan, 1992 .

An Efficient Algorithm for Computing Free Disk&e

Lalit R. Bahl, F. Jelinek, W. D. Frazer, 1971 .

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

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1981, ICASSP.

Recognition results for several experimental acoustic processors

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1979, ICASSP.

Statistical modeling and automatic parameter estimation in speech recognition

Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, 1976 .

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

Lalit R. Bahl, Ponani S. Gopalakrishnan, Mukund Padmanabhan, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

Automatic phonetic baseform determination

Michael Picheny, Bernard Mérialdo, Lalit R. Bahl, 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.