Peter V. de Souza

30 papers Misc 16Journal 7Unranked 7
YearRankTypeTitle / Venue / Authors
1999 — conf
Enhanced likelihood computation using regression.
EUROSPEECH
Peter V. de Souza, Bhuvana Ramabhadran, Yuqing Gao, Michael Picheny
1995 Misc conf
Experiments using data augmentation for speaker adaptation.
ICASSP
Jerome R. Bellegarda, Peter V. de Souza, David Nahamoo, Mukund Padmanabhan, Michael A. Picheny, Lalit R. Bahl
1994 — conf
Robust methods for using context-dependent features and models in a continuous speech recognizer.
ICASSP (1)
Lalit R. Bahl, Peter V. de Souza, Ponani S. Gopalakrishnan, David Nahamoo, Michael A. Picheny
1994 J jnl
The metamorphic algorithm: a speaker mapping approach to data augmentation.
IEEE Trans. Speech Audio Process.
Jerome R. Bellegarda, Peter V. de Souza, Arthur Nádas, David Nahamoo, Michael A. Picheny, Lalit R. Bahl
1993 J jnl
A method for the construction of acoustic Markov models for words.
IEEE Trans. Speech Audio Process.
Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer, Michael A. Picheny
1993 — conf
A supervised approach to the construction of context-sensitive acoustic prototypes.
ICASSP (2)
Jerome R. Bellegarda, Peter V. de Souza, David Nahamoo, Michael A. Picheny, Lalit R. Bahl
1993 — conf
Context dependent vector quantization for continuous speech recognition.
ICASSP (2)
Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, Michael A. Picheny
1993 J jnl
Estimating hidden Markov model parameters so as to maximize speech recognition accuracy.
IEEE Trans. Speech Audio Process.
Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer
1993 J jnl
Multonic Markov word models for large vocabulary continuous speech recognition.
IEEE Trans. Speech Audio Process.
Lalit R. Bahl, Jerome R. Bellegarda, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael A. Picheny
1993 — conf
Word lookahead scheme for cross-word right context models in a stack decoder.
EUROSPEECH
Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael Picheny
1992 Misc conf
A fast match for continuous speech recognition using allophonic models.
ICASSP
Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael A. Picheny
1992 Misc conf
Adaptation of large vocabulary recognition system parameters.
ICASSP
Lalit R. Bahl, Peter V. de Souza, David Nahamoo, Michael A. Picheny, Salim Roukos
1992 J jnl
Class-Based n-gram Models of Natural Language.
Comput. Linguistics
Peter F. Brown, Vincent J. Della Pietra, Peter V. de Souza, Jennifer C. Lai, Robert L. Mercer
1992 J jnl
Constructing candidate word lists using acoustically similar word groups.
IEEE Trans. Signal Process.
Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, Dimitri Kanevsky, David Nahamoo
1992 Misc conf
Robust speaker adaptation using a piecewise linear acoustic mapping.
ICASSP
Jerome R. Bellegarda, Peter V. de Souza, Arthur Nádas, David Nahamoo, Michael A. Picheny, Lalit R. Bahl
1991 — conf
A fast algorithm for deleted interpolation.
EUROSPEECH
Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer, David Nahamoo
1991 Misc conf
A new class of fenonic Markov word models for large vocabulary continuous speech recognition.
ICASSP
Lalit R. Bahl, Jerome R. Bellegarda, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael A. Picheny
1991 — conf
Context Dependent Modeling of Phones in Continuous Speech Using Decision Trees.
HLT
Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael Picheny
1991 Misc conf
Decision trees for phonological rules in continuous speech.
ICASSP
Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, David Nahamoo, Michael A. Picheny
1990 Misc conf
Constructing groups of acoustically confusable words.
ICASSP
Lalit R. Bahl, Peter V. de Souza, P. S. Gopalakrishnan, Dimitri Kanevsky, David Nahamoo
1989 J jnl
A tree-based statistical language model for natural language speech recognition.
IEEE Trans. Acoust. Speech Signal Process.
Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer
1989 Misc conf
Large vocabulary natural language continuous speech recognition.
ICASSP
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
1988 Misc conf
A new algorithm for the estimation of hidden Markov model parameters.
ICASSP
Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer
1988 Misc conf
Acoustic Markov models used in the Tangora speech recognition system.
ICASSP
Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer, Michael A. Picheny
1988 Misc conf
Obtaining candidate words by polling in a large vocabulary speech recognition system.
ICASSP
Lalit R. Bahl, Raimo Bakis, Peter V. de Souza, Robert L. Mercer
1988 Misc conf
Speech recognition with continuous-parameter hidden Markov models.
ICASSP
Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer
1987 Misc conf
Experiments with the Tangora 20, 000 word speech recognizer.
ICASSP
Amir Averbuch, Lalit R. Bahl, Raimo Bakis, Peter F. Brown, Gregg 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
1986 Misc conf
An IBM PC based large-vocabulary isolated-utterance speech recognizer.
ICASSP
Amir Averbuch, Lalit R. Bahl, Raimo Bakis, Peter F. Brown, A. G. Cole, Gregg 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
1986 Misc conf
Maximum mutual information estimation of hidden Markov model parameters for speech recognition.
ICASSP
Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer
1984 Misc conf
Some experiments with large-vocabulary isolated-word sentence recognition.
ICASSP
Lalit R. Bahl, Subrata K. Das, Peter V. de Souza, Frederick Jelinek, Slava M. Katz, Robert L. Mercer, Michael A. Picheny