Herbert Gish

Publication Activity (10 Years)

Years Active: 1968-2020
Publications (10 Years): 4

Top Topics

Training Dataset

Importance Sampling

Top Venues

Comput. Speech Lang.

Publications

Zhuolin Jiang, Jan Silovský, Man-Hung Siu, William Hartmann, Herbert Gish, Sancar Adali
Learning from Noisy Labels with Noise Modeling Network. CoRR (2020)
Herbert Gish, Jan Silovský, Man-Ling Sung, Man-Hung Siu, William Hartmann, Zhuolin Jiang
Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data. ICASSP (2020)
Herbert Gish, Jan Silovský, Man-Ling Sung, Man-Hung Siu, William Hartmann, Zhuolin Jiang
Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data. CoRR (2019)
Kerri Barnes, Matthew Snover, Man-Hung Siu, Herbert Gish
Importance sampling of delta-AUC: A basis for active learning for improved keyword search. ICASSP (2016)
Man-Hung Siu, Herbert Gish, Arthur Chan, William Belfield, Steve Lowe
Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery. Comput. Speech Lang. 28 (1) (2014)
Man-Hung Siu, Omer Lang, Herbert Gish, Stephen A. Lowe, Arthur Chan, Owen Kimball
MLLR transforms of self-organized units as features in speaker recognition. ICASSP (2012)
Man-Hung Siu, Herbert Gish, Steve Lowe, Arthur Chan
Unsupervised Audio Patterns Discovery Using HMM-Based Self-Organized Units. INTERSPEECH (2011)
Timothy J. Hazen, Man-Hung Siu, Herbert Gish, Steve Lowe, Arthur Chan
Topic modeling for spoken documents using only phonetic information. ASRU (2011)
Man-Hung Siu, Herbert Gish, Arthur Chan, William Belfield
Improved topic classification and keyword discovery using an HMM-based speech recognizer trained without supervision. INTERSPEECH (2010)
Man-Hung Siu, Xi Yang, Herbert Gish
Discriminatively Trained GMMs for Language Classification Using Boosting Methods. IEEE Trans. Speech Audio Process. 17 (1) (2009)
Herbert Gish, Man-Hung Siu, Arthur Chan, William Belfield
Unsupervised training of an HMM-based speech recognizer for topic classification. INTERSPEECH (2009)
David R. H. Miller, Michael Kleber, Chia-Lin Kao, Owen Kimball, Thomas Colthurst, Stephen A. Lowe, Richard M. Schwartz, Herbert Gish
Rapid and accurate spoken term detection. INTERSPEECH (2007)
Xi Yang, Man-Hung Siu, Herbert Gish, Brian Mak
Boosting with anti-models for automatic language identification. INTERSPEECH (2007)
Xi Yang, Lu-Feng Zhai, Man-Hung Siu, Herbert Gish
Improved language identification using support vector machines for language modeling. INTERSPEECH (2006)
Lu-Feng Zhai, Man-Hung Siu, Xi Yang, Herbert Gish
Discriminatively trained Language Models using Support Vector Machines for Language Identification. Odyssey (2006)
Alvin Garcia, Herbert Gish
Keyword Spotting of Arbitrary Words Using Minimal Speech Resources. ICASSP (1) (2006)
Richard M. Schwartz, Thomas Colthurst, Nicolae Duta, Herbert Gish, Rukmini Iyer, Chia-Lin Kao, Daben Liu, Owen Kimball, Jeff Z. Ma, John Makhoul, Spyros Matsoukas, Long Nguyen, Mohammed Noamany, Rohit Prasad, Bing Xiang, Dongxin Xu, Jean-Luc Gauvain, Lori Lamel, Holger Schwenk, Gilles Adda, Langzhou Chen
Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system. ICASSP (3) (2004)
William Belfield, Herbert Gish
A topic classification system based on parametric trajectory mixture models. INTERSPEECH (2003)
Rukmini Iyer, Herbert Gish, Dan McCarthy
Unsupervised training techniques for natural language call routing. ICASSP (2002)
Owen Kimball, Rukmini Iyer, Herbert Gish, Scott Miller, Fred Richardson
Extracting descriptive noun phrases from conversational speech. ICASSP (2002)
Rukmini Iyer, Jeffrey Z. Ma, Herbert Gish, Owen Kimball
Training topic classifiers for conversational speech with limited data. INTERSPEECH (2002)
Spyros Matsoukas, Thomas Colthurst, Owen Kimball, Alex Solomonoff, Fred Richardson, Carl Quillen, Herbert Gish, Pierre L. Dognin
The 2001 BYBLOS English large vocabulary conversational speech recognition system. ICASSP (2002)
Thomas Colthurst, Owen Kimball, Fred Richardson, Han Shu, Chuck Wooters, Rukmini Iyer, Herbert Gish
The 2000 BBN Byblos LVCSR system. INTERSPEECH (2000)
Han Shu, Chuck Wooters, Owen Kimball, Thomas Colthurst, Fred Richardson, Spyros Matsoukas, Herbert Gish
The BBN Byblos 2000 conversational Mandarin LVCSR system. INTERSPEECH (2000)
John Golden, Owen Kimball, Man-Hung Siu, Herbert Gish
Automatic topic identification for two-level call routing. ICASSP (1999)
Man-Hung Siu, Michael Jonas, Herbert Gish
Using a large vocabulary continuous speech recognizer for a constrained domain with limited training. ICASSP (1999)
Jayadev Billa, Thomas Colthurst, Amro El-Jaroudi, Rukmini Iyer, Kristine W. Ma, Spyridon Matsoukas, Carl Quillen, Fred Richardson, Man-Hung Siu, George Zavaliagkos, Herbert Gish
Recent experiments in large vocabulary conversational speech recognition. ICASSP (1999)
Rukmini Iyer, Owen Kimball, Herbert Gish
Modeling trajectories in the HMM framework. EUROSPEECH (1999)
Man-Hung Siu, Herbert Gish
Evaluation of word confidence for speech recognition systems. Comput. Speech Lang. 13 (4) (1999)
Man-Hung Siu, Rukmini Iyer, Herbert Gish, Carl Quillen
Parametric trajectory mixtures for LVCSR. ICSLP (1998)
George Zavaliagkos, John W. McDonough, David R. Miller, Amro El-Jaroudi, Jayadev Billa, Fred Richardson, Kristine W. Ma, Man-Hung Siu, Herbert Gish
The BBN Byblos 1997 large vocabulary conversational speech recognition system. ICASSP (1998)
Rukmini Iyer, Herbert Gish, Man-Hung Siu, George Zavaliagkos, Spyros Matsoukas
Hidden Markov models for trajectory modeling. ICSLP (1998)
Alex Solomonoff, Angela Mielke, Michael Schmidt, Herbert Gish
Clustering speakers by their voices. ICASSP (1998)
Man-Hung Siu, Herbert Gish, Fred Richardson
Improved estimation, evaluation and applications of confidence measures for speech recognition. EUROSPEECH (1997)
Rukmini Iyer, Mari Ostendorf, Herbert Gish
Using out-of-domain data to improve in-domain language models. IEEE Signal Process. Lett. 4 (8) (1997)
Owen Kimball, Michael Schmidt, Herbert Gish, Jason Waterman
Speaker verification with limited enrollment data. EUROSPEECH (1997)
John W. McDonough, Tasos Anastasakos, George Zavaliagkos, Herbert Gish
Speaker-adapted training on the Switchboard Corpus. ICASSP (1997)
Michael Schmidt, John Golden, Herbert Gish
GMM sample statistic log-likelihoods for text-independent speaker recognition. EUROSPEECH (1997)
Michael Schmidt, Herbert Gish
Speaker identification via support vector classifiers. ICASSP (1996)
Herbert Gish, Kenney Ng
Parametric trajectory models for speech recognition. ICSLP (1996)
Michael A. Lund, Kristine W. Ma, Herbert Gish
Statistical language identification based on untranscribed training. ICASSP (1996)
John W. McDonough, George Zavaliagkos, Herbert Gish
An approach to speaker adaptation based on analytic functions. ICASSP (1996)
Ellen Eide, Herbert Gish
A parametric approach to vocal tract length normalization. ICASSP (1996)
Michael Schmidt, Herbert Gish, Angela Mielke
Covariance estimation methods for channel robust text-independent speaker identification. ICASSP (1995)
Philippe Jeanrenaud, Ellen Eide, Upendra V. Chaudhari, John W. McDonough, Kenney Ng, Man-Hung Siu, Herbert Gish
Reducing word error rate on conversational speech from the Switchboard corpus. ICASSP (1995)
Philippe Jeanrenaud, Man-Hung Siu, Herbert Gish
Large vocabulary word scoring as a basis for transcription generation. EUROSPEECH (1995)
Douglas Cochran, Herbert Gish, Dana Sinno
A geometric approach to multiple-channel signal detection. IEEE Trans. Signal Process. 43 (9) (1995)
Michael A. Lund, Herbert Gish
Two novel language model estimation techniques for statistical language identification. EUROSPEECH (1995)
Ellen Eide, Herbert Gish, Philippe Jeanrenaud, Angela Mielke
Understanding and improving speech recognition performance through the use of diagnostic tools. ICASSP (1995)
Man-Hung Siu, Herbert Gish, Jan Robin Rohlicek
Predicting word spotting performance. ICSLP (1994)
Herbert Gish, Man-Hung Siu
An invariance property of neural networks. ICASSP (2) (1994)
Philippe Jeanrenaud, Man-Hung Siu, Jan Robin Rohlicek, Marie Meteer, Herbert Gish
Spotting events in continuous speech. ICASSP (1) (1994)
Herbert Gish, Michael Schmidt, Angela Mielke
A robust, segmental method for text independent speaker identification. ICASSP (1) (1994)
John W. McDonough, Herbert Gish
Issues in topic identification on the switchboard corpus. ICSLP (1994)
John W. McDonough, Kenney Ng, Philippe Jeanrenaud, Herbert Gish, Jan Robin Rohlicek
Approaches to topic identification on the switchboard corpus. ICASSP (1) (1994)
Herbert Gish, Michael Schmidt
Text-independent speaker identification. IEEE Signal Process. Mag. 11 (4) (1994)
Philippe Jeanrenaud, Kenney Ng, Man-Hung Siu, Jan Robin Rohlicek, Herbert Gish
Phonetic-based word spotter: various configurations and application to event spotting. EUROSPEECH (1993)
L. Denenberg, Herbert Gish, Marie Meteer, T. Miller, Jan Robin Rohlicek, W. Sadkin, Man-Hung Siu
Gisting conversational speech in real time. ICASSP (2) (1993)
Jan Robin Rohlicek, Philippe Jeanrenaud, Kenney Ng, Herbert Gish, Bruce R. Musicus, Man-Hung Siu
Phonetic training and language modeling for word spotting. ICASSP (2) (1993)
Ellen Eide, Jan Robin Rohlicek, Herbert Gish, Sanjoy Mitter
A linguistic feature representation of the speech waveform. ICASSP (2) (1993)
George Yu, Herbert Gish
Identification of speakers engaged in dialog. ICASSP (2) (1993)
Herbert Gish, Kenney Ng
A segmental speech model with applications to word spotting. ICASSP (2) (1993)
Ralph M. Weischedel, Damaris M. Ayuso, Sean Boisen, Heidi Fox, Herbert Gish, Robert Ingria
BBN PLUM: MUC-4 test results and analysis. MUC (1992)
Jan Robin Rohlicek, Damaris M. Ayuso, Madeleine Bates, Robert J. Bobrow, A. Boulanger, Herbert Gish, Philippe Jeanrenaud, Marie Meteer, Man-Hung Siu
Gisting conversational speech. ICASSP (1992)
Herbert Gish
A minimum classification error, maximum likelihood, neural network. ICASSP (1992)
Kenney Ng, Herbert Gish, Jan Robin Rohlicek
Robust mapping of noisy speech parameters for HMM word spotting. ICASSP (1992)
Man-Hung Siu, George Yu, Herbert Gish
An unsupervised, sequential learning algorithm for the segmentation of speech waveforms with multiple speakers. ICASSP (1992)
Herbert Gish, Kenney Ng, Jan Robin Rohlicek
Secondary processing using speech segments for an HMM word spotting system. ICSLP (1992)
Damaris M. Ayuso, Sean Boisen, Heidi Fox, Herbert Gish, Robert Ingria, Ralph M. Weischedel
BBN: description of the PLUM system as used for MUC-4. MUC (1992)
Douglas Cochran, Dana Sinno, Herbert Gish
A comparison of nonparametric statistics for multiple-channel detection of signals in ocean noise. ICASSP (1991)
Herbert Gish, Man-Hung Siu, Jan Robin Rohlicek
Segregation of speakers for speech recognition and speaker identification. ICASSP (1991)
Herbert Gish
A probabilistic approach to the understanding and training of neural network classifiers. ICASSP (1990)
Douglas Cochran, Herbert Gish
Multiple-channel detection using generalized coherence. ICASSP (1990)
Herbert Gish
Robust discrimination in automatic speaker identification. ICASSP (1990)
Herbert Gish, Yen-Lu Chow, Jan Robin Rohlicek
Probabilistic vector mapping of noisy speech parameters for HMM word spotting. ICASSP (1990)
Jan Robin Rohlicek, William Russell, Salim Roukos, Herbert Gish
Continuous hidden Markov modeling for speaker-independent word spotting. ICASSP (1989)
Herbert Gish, Ronald A. Mucci
Detection of multiple signals by the significance test. ICASSP (1989)
Herbert Gish, Douglas Cochran
Generalized coherence [signal detection]. ICASSP (1988)
Salim E. Roucos, Mari Ostendorf, Herbert Gish, Alan Derr
Stochastic segment modelling using the estimate-maximize algorithm [speech recognition]. ICASSP (1988)
Herbert Gish, Douglas Cochran
Invariance of the magnitude-squared coherence estimate with respect to second-channel statistics. IEEE Trans. Acoust. Speech Signal Process. 35 (12) (1987)
Herbert Gish, Michael A. Krasner, William Russell, Jared J. Wolf
Methods and experiments for text-independent speaker recognition over telephone channels. ICASSP (1986)
Herbert Gish, Kenneth F. Karnofsky, Michael A. Krasner, Salim E. Roucos, Richard M. Schwartz, Jared J. Wolf
Investigation of text-independent speaker indentification over telephone channels. ICASSP (1985)
John Makhoul, Salim E. Roucos, Herbert Gish
Vector quantization in speech coding. Proc. IEEE 73 (11) (1985)
Michael A. Krasner, Jared J. Wolf, Kenneth F. Karnofsky, Richard M. Schwartz, Salim E. Roucos, Herbert Gish
Investigation of text-independent speaker identification techniques under conditions of variable data. ICASSP (1984)
Herbert Gish
The magnitude squared coherence estimate: A geometric view. ICASSP (1984)
Herbert Gish, John N. Pierce
Asymptotically efficient quantizing. IEEE Trans. Inf. Theory 14 (5) (1968)