Herbert Gish

发表

Approaches to topic identification on the switchboard corpus

Herbert Gish, Kenney Ng, John W. McDonough, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Segregation of speakers for speech recognition and speaker identification

Herbert Gish, Man-Hung Siu, Jan Robin Rohlicek, 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

The BBN Byblos 1997 large vocabulary conversational speech recognition system

Herbert Gish, Amro El-Jaroudi, George Zavaliagkos, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Topic modeling for spoken documents using only phonetic information

Herbert Gish, Man-Hung Siu, Steve Lowe, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

The BBN Byblos 2000 conversational Mandarin LVCSR system

Herbert Gish, Spyridon Matsoukas, Thomas Colthurst, 2000, INTERSPEECH.

Parametric trajectory mixtures for LVCSR

Herbert Gish, Rukmini Iyer, Man-Hung Siu, 1998, ICSLP.

Improved language identification using support vector machines for language modeling

Herbert Gish, Xi Yang, Man-Hung Siu, 2006, INTERSPEECH.

Stochastic segment modelling using the estimate-maximize algorithm (speech recognition)

Herbert Gish, M. Ostendorf, S. Roucos, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

Towards a New Understanding of the Training of Neural Networks with Mislabeled Training Data

Herbert Gish, Man-Hung Siu, Zhuolin Jiang, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unsupervised training techniques for natural language call routing

Herbert Gish, Rukmini Iyer, Dan McCarthy, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A parametric approach to vocal tract length normalization

Herbert Gish, Ellen Eide, H. Gish, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

Unsupervised training of an HMM-based speech recognizer for topic classification

Herbert Gish, Man-Hung Siu, Arthur Chan, 2009, INTERSPEECH.

The magnitude squared coherence estimate: A geometric view

Herbert Gish, 1984, ICASSP.

in Automatic Speaker Identification

Herbert Gish, Bbn Systems, 1990 .

Elements of Speaker Verification

Herbert Gish, H. Gish, 2005 .

Speaker identification via support vector classifiers

Herbert Gish, Michael Schmidt, H. Gish, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

Investigation of Problems in the Communication of Analog Data.

Herbert Gish, 1969 .

Asymptotically efficient quantizing

Herbert Gish, John N. Pierce, H. Gish, 1968, IEEE Trans. Inf. Theory.

The 2001 BYBLOS English large vocabulary conversational speech recognition system

Herbert Gish, Spyridon Matsoukas, Thomas Colthurst, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A geometrical approach to multiple-channel detection

Herbert Gish, Douglas Cochran, H. Gish, 1990 .

Identification of speakers engaged in dialog

Herbert Gish, George Yu, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

The 2000 BBN Byblos LVCSR system

Herbert Gish, Thomas Colthurst, Owen Kimball, 2000, INTERSPEECH.

Importance sampling of delta-AUC: A basis for active learning for improved keyword search

Herbert Gish, Man-Hung Siu, Matthew G. Snover, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Phonetic-based word spotter: various configurations and application to event spotting

Herbert Gish, Kenney Ng, Man-Hung Siu, 1993, EUROSPEECH.

Predicting word spotting performance

Herbert Gish, Man-Hung Siu, Jan Robin Rohlicek, 1994, ICSLP.

Hidden Markov models for trajectory modeling

Herbert Gish, George Zavaliagkos, Spyridon Matsoukas, 1998, ICSLP.

Gisting conversational speech in real time

Herbert Gish, T. Miller, Jan Robin Rohlicek, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Covariance estimation methods for channel robust text-independent speaker identification

Herbert Gish, Michael Schmidt, Angela Mielke, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

A robust, segmental method for text independent speaker identification

Herbert Gish, Michael Schmidt, Angela Mielke, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

A device for detection of conversation topics

Herbert Gish, W Mcdonough, Robin Rohlicek, 1995 .

GMM sample statistic log-likelihoods for text-independent speaker recognition

Herbert Gish, Michael Schmidt, John Golden, 1997, EUROSPEECH.

Speaker-adapted training on the Switchboard Corpus

Herbert Gish, George Zavaliagkos, John W. McDonough, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Invariance of the magnitude-squared coherence estimate with respect to second-channel statistics

Herbert Gish, Douglas Cochran, 1987, IEEE Trans. Acoust. Speech Signal Process..

A New Approach to Target Detection and Estimation in Clutter

Herbert Gish, Yaakov Bar-Shalom, Ronald Mucci, 1985, 1985 American Control Conference.

Extracting descriptive noun phrases from conversational speech

Herbert Gish, Owen Kimball, Rukmini Iyer, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Issues in topic identification on the switchboard corpus

Herbert Gish, John W. McDonough, H. Gish, 1994, ICSLP.

Two novel language model estimation techniques for statistical language identification

Herbert Gish, Michael A. Lund, H. Gish, 1995, EUROSPEECH.

Reducing word error rate on conversational speech from the Switchboard corpus

Herbert Gish, Kenney Ng, John W. McDonough, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

MLLR transforms of self-organized units as features in speaker recognition

Herbert Gish, Owen Kimball, Man-Hung Siu, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An invariance property of neural networks

Herbert Gish, Man-Hung Siu, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Improved topic classification and keyword discovery using an HMM-based speech recognizer trained without supervision

Herbert Gish, Man-Hung Siu, Arthur Chan, 2010, INTERSPEECH.

Learning from Noisy Labels with Noise Modeling Network pdf

Herbert Gish, William Hartmann, Man-Hung Siu, 2020, ArXiv.

Investigation of text-independent speaker identification techniques under conditions of variable data

Herbert Gish, Richard M. Schwartz, Salim E. Roucos, 1984, ICASSP.

A segmental speech model with applications to word spotting

Herbert Gish, Kenney Ng, H. Gish, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Understanding and improving speech recognition performance through the use of diagnostic tools

Herbert Gish, Philippe Jeanrenaud, Angela Mielke, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

Secondary processing using speech segments for an HMM word spotting system

Herbert Gish, Kenney Ng, Jan Robin Rohlicek, 1992, ICSLP.

BBN: Description of the PLUM System as Used for MUC-5

Herbert Gish, Ralph M. Weischedel, Robert Ingria, 2005, MUC.

Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system

Herbert Gish, Richard M. Schwartz, John Makhoul, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Training topic classifiers for conversational speech with limited data

Herbert Gish, Jeff Z. Ma, Owen Kimball, 2002, INTERSPEECH.

Investigation of text-independent speaker indentification over telephone channels

Herbert Gish, K. Karnofsky, J. Wolf, 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Unsupervised Audio Patterns Discovery Using HMM-Based Self-Organized Units

Herbert Gish, Man-Hung Siu, Steve Lowe, 2011, INTERSPEECH.

Rapid and accurate spoken term detection

Herbert Gish, Richard M. Schwartz, Chia-Lin Kao, 2007, INTERSPEECH.

Using a large vocabulary continuous speech recognizer for a constrained domain with limited training

Herbert Gish, Man-Hung Siu, Michael Jonas, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Discriminatively trained Language Models using Support Vector Machines for Language Identification

Herbert Gish, Xi Yang, Man-Hung Siu, 2006, 2006 IEEE Odyssey - The Speaker and Language Recognition Workshop.

Recent experiments in large vocabulary conversational speech recognition

Herbert Gish, Amro El-Jaroudi, George Zavaliagkos, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Speaker verification with limited enrollment data

Herbert Gish, Owen Kimball, Michael Schmidt, 1997, EUROSPEECH.

Modeling trajectories in the HMM framework

Herbert Gish, Owen Kimball, Rukmini Iyer, 1999, EUROSPEECH.

Evaluation of word confidence for speech recognition systems

Herbert Gish, Man-Hung Siu, H. Gish, 1999, Comput. Speech Lang..

Large vocabulary word scoring as a basis for transcription generation

Herbert Gish, Man-Hung Siu, Philippe Jeanrenaud, 1995, EUROSPEECH.

Spotting events in continuous speech

Herbert Gish, Man-Hung Siu, Philippe Jeanrenaud, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Weak target detection using the entropy concept

Herbert Gish, 1990, Defense + Commercial Sensing.

Boosting with anti-models for automatic language identification

Herbert Gish, Xi Yang, Man-Hung Siu, 2007, INTERSPEECH.

Unsupervised training of an HMM-based self-organizing unit recognizer with applications to topic classification and keyword discovery

Herbert Gish, Man-Hung Siu, Steve Lowe, 2014, Comput. Speech Lang..

Methods and experiments for text-independent speaker recognition over telephone channels

Herbert Gish, J. Wolf, W. Russell, 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

Discriminatively Trained GMMs for Language Classification Using Boosting Methods

Herbert Gish, Xi Yang, Man-Hung Siu, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

Parametric trajectory models for speech recognition

Herbert Gish, Kenney Ng, H. Gish, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

Digital Modulation Enhancement Study

Herbert Gish, 1973 .

A geometric approach to multiple-channel signal detection

Herbert Gish, Douglas Cochran, Dana Sinno, 1995, IEEE Trans. Signal Process..

Adaptive Natural Language Processing

Herbert Gish, Robert Ingria, Robert J. Bobrow, 1991 .

Improved estimation, evaluation and applications of confidence measures for speech recognition

Herbert Gish, Man-Hung Siu, Fred Richardson, 1997, EUROSPEECH.

A topic classification system based on parametric trajectory mixture models

Herbert Gish, William Belfield, 2003, INTERSPEECH.

Automatic topic identification for two-level call routing

Herbert Gish, Owen Kimball, Man-Hung Siu, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Keyword Spotting of Arbitrary Words Using Minimal Speech Resources

Herbert Gish, Alvin Garcia, H. Gish, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Phonetic training and language modeling for word spotting

Herbert Gish, Kenney Ng, Philippe Jeanrenaud, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Clustering speakers by their voices

Herbert Gish, Alex Solomonoff, Michael Schmidt, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

An approach to speaker adaptation based on analytic functions

Herbert Gish, George Zavaliagkos, John W. McDonough, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

Weak target detection using the entropy concept

Herbert Gish, Ronald Mucci, 1990 .

Target State Estimation in a Multitarget Environment Using Multiple Sensors

Herbert Gish, Ronald Mucci, 1987, IEEE Transactions on Aerospace and Electronic Systems.