M. Picheny

发表

Some experiments with large-vocabulary isolated-word sentence recognition

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

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

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

Large vocabulary natural language continuous speech recognition

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

Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences

M. Picheny, M. Padmanabhan, M. Padmanabhan, 2017 .

Deep Belief Networks using discriminative features for phone recognition

Tara N. Sainath, Bhuvana Ramabhadran, Michael Picheny, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An exploration of large vocabulary tools for small vocabulary phonetic recognition

Tara N. Sainath, Bhuvana Ramabhadran, Michael Picheny, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

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.

Lattice-based Viterbi decoding techniques for speech translation

George Saon, Michael Picheny, M. Picheny, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

Innovative approaches for large vocabulary name recognition

Bhuvana Ramabhadran, Michael Picheny, Hakan Erdogan, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

On a model-robust training method for speech recognition

Michael Picheny, David Nahamoo, Arthur Nádas, 1988, IEEE Trans. Acoust. Speech Signal Process..

Parallel Deep Neural Network Training for Big Data on Blue Gene/Q

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2017, IEEE Trans. Parallel Distributed Syst..

New Adaptation Techniques for Large Vocabulary Continuous Speech Recognition

M. Picheny, B. Ramabhadran, Yuqing Gao, 2003 .

Kernel Approximation Methods for Speech Recognition

Brian Kingsbury, Michael Picheny, Michael Collins, 2017, J. Mach. Learn. Res..

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..

The IBM 2015 English conversational telephone speech recognition system pdf

George Saon, Michael Picheny, Hong-Kwang Jeff Kuo, 2015, INTERSPEECH.

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.

Context Dependent Modeling of Phones in Continuous Speech Using Decision Trees

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

Speaking clearly for the hard of hearing. II: Acoustic characteristics of clear and conversational speech.

M. Picheny, L. Braida, N. Durlach, 1986, Journal of speech and hearing research.

A CORPUS-BASED APPROACH TO < AHEM / > EXPRESSIVE SPEECH SYNTHESIS

R. Bakis, M. Picheny, E. Eide, 2004 .

The metamorphic algorithm: a speaker mapping approach to data augmentation

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

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.

Influence of background noise and microphone on the performance of the IBM Tangora speech recognition system

Michael Picheny, David Nahamoo, Raimo Bakis, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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.

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.

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.

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.

Speech recognition using noise-adaptive prototypes

Michael Picheny, David Nahamoo, Arthur Nádas, 1989, IEEE Trans. Acoust. Speech Signal Process..

Speaker adaptation based on pre-clustering training speakers

Michael Picheny, Yuqing Gao, Mukund Padmanabhan, 1997, EUROSPEECH.

Recurrent Neural Networks for Speech Recognition

M. Picheny, H. Soltau, G. Saon, 2014 .

Hidden Markov Models in

M. Picheny, Stanley F. Chen, B. Ramabhadran, 1993 .

Towards super-human speech recogniton

M. Picheny, M. Padmanabhan, 2003 .

Speaking clearly for the hard of hearing I: Intelligibility differences between clear and conversational speech.

N I Durlach, L D Braida, M. Picheny, 1985, Journal of speech and hearing research.

Speaking clearly for the hard of hearing. III: An attempt to determine the contribution of speaking rate to differences in intelligibility between clear and conversational speech.

N I Durlach, L D Braida, M. Picheny, 1989, Journal of speech and hearing research.

Speech Signal Processing

Bhuvana Ramabhadran, Michael Picheny, Jerry D. Gibson, 1997, Circuits, Signals, and Speech and Image Processing.

Speaking clearly for the hard of hearing

M. Picheny, N. Durlach, 1979 .

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

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

Robust speech recognition in noise --- performance of the IBM continuous speech recogniser on the ARPA noise spoke task

Michael Picheny, Ponani S. Gopalakrishnan, Mark J. F. Gales, 1995 .

Fourth International Workshop on Computation Advances in Multisensor Adaptive Processing (CAMSAP)

Michael Picheny, Zhengyou Zhang, Anthony Vetro, 2011 .

Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos pdf

James Glass, Brian Kingsbury, Michael Picheny, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

New methods in continuous Mandarin speech recognition

Michael Picheny, Ramesh A. Gopinath, Michael D. Monkowski, 1997, EUROSPEECH.

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

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

(SPECIAL SECTION - SIGNAL PROCESSING FOR SOUND SYNTHESIS )

Rabab K. Ward, Petar M. Djuric, Sergios Theodoridis, 2007 .

Direct Acoustics-to-Word Models for English Conversational Speech Recognition

M. Picheny, D. Nahamoo, B. Ramabhadran, 2017, Interspeech.

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos

James R. Glass, A. Torralba, M. Picheny, 2020, Interspeech.

Towards Disentangled Speech Representations

Kyunghyun Cho, M. Picheny, Cal Peyser, 2022, INTERSPEECH.

Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks pdf

Wei Zhang, Xiaodong Cui, Michael Picheny, 2018, NeurIPS.

Semi-Supervised Training and Data Augmentation for Adaptation of Automatic Broadcast News Captioning Systems

Michael Picheny, Zoltán Tüske, Masayuki Suzuki, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Detection and Recovery of OOVs for Improved English Broadcast News Captioning

Michael Picheny, Samuel Thomas, Kartik Audhkhasi, 2019, INTERSPEECH.

Acoustically Grounded Word Embeddings for Improved Acoustics-to-word Speech Recognition

Michael Picheny, Karen Livescu, Kartik Audhkhasi, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Effects of automated transcription quality on non-native speakers' comprehension in real-time computer-mediated communication

Michael Picheny, Lin Yao, Danning Jiang, 2010, CHI.

Heredity and environment in speech recognition: the role of a priori information vs. data

Michael Picheny, M. Picheny, 2000, INTERSPEECH.

Neural Network Training Variations in Speech and Subsequent Performance Evaluation

Bhuvana Ramabhadran, Michael Picheny, Ewout van den Berg, 2016 .

Towards automatic transcription of large spoken archives - English ASR for the MALACH project

Jing Huang, Bhuvana Ramabhadran, Michael Picheny, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

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.

Recent advances in speech recognition system for IBM DARPA communicator

Michael Picheny, Vaibhava Goel, Hakan Erdogan, 2001, INTERSPEECH.

Speech recognition using noise-adaptive prototypes

A. Nadas, D. Nahamoo, M.A. Picheny, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

Recent advances in conversational speech recognition using convolutional and recurrent neural networks

George Saon, Michael Picheny, M. Picheny, 2017, IBM J. Res. Dev..

Recent progress in deep end-to-end models for spoken language processing

Bhuvana Ramabhadran, George Saon, Michael Picheny, 2017, IBM J. Res. Dev..

Rapid adaptation using penalized-likelihood methods

Michael Picheny, Hakan Erdogan, Yuqing Gao, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale

Tara N. Sainath, Kyunghyun Cho, M. Picheny, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Toward domain-independent conversational speech recognition

Geoffrey Zweig, Brian Kingsbury, George Saon, 2003, INTERSPEECH.

Using semantic analysis to improve speech recognition performance

Michael Picheny, Ruhi Sarikaya, Hakan Erdogan, 2005, Comput. Speech Lang..

Cultural voice markers in speech-to-speech machine translation systems

Bhuvana Ramabhadran, Michael Picheny, Osamuyimen Stewart, 2009, IWIC '09.

Speaker adaptation of neural network acoustic models using i-vectors

George Saon, Hagen Soltau, Michael Picheny, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Grounding Spoken Words in Unlabeled Video

Michael Picheny, James R. Glass, Antonio Torralba, 2019, CVPR Workshops.

End-to-end speech recognition and keyword search on low-resource languages

Bhuvana Ramabhadran, Michael Picheny, Andrew Rosenberg, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs pdf

Michael Picheny, Samuel Thomas, Edmilson Morais, 2021, Interspeech.

Acoustic Model Optimization Based On Evolutionary Stochastic Gradient Descent with Anchors for Automatic Speech Recognition pdf

Michael Picheny, Xiaodong Cui, M. Picheny, 2019, INTERSPEECH.

A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition pdf

Brian Kingsbury, George Saon, Michael Picheny, 2019, INTERSPEECH.

Distributed Deep Learning Strategies for Automatic Speech Recognition

Xiaodong Cui, Brian Kingsbury, George Saon, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems

Brian Kingsbury, Michael Picheny, Samuel Thomas, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions pdf

Michael Picheny, Leda Sari, Caner Hazirbas, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cascaded Multilingual Audio-Visual Learning from Videos pdf

James Glass, Brian Kingsbury, Michael Picheny, 2021, Interspeech.

Pre-training of Speaker Embeddings for Low-latency Speaker Change Detection in Broadcast News

Michael Picheny, Mark Hasegawa-Johnson, Samuel Thomas, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition

Brian Kingsbury, Bhuvana Ramabhadran, George Saon, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multilingual representations for low resource speech recognition and keyword search

Brian Kingsbury, Bhuvana Ramabhadran, Michael Picheny, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

The IBM expressive text-to-speech synthesis system for American English

Michael Picheny, Raimo Bakis, John F. Pitrelli, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

English Conversational Telephone Speech Recognition by Humans and Machines

Xiaodong Cui, Bhuvana Ramabhadran, George Saon, 2017, INTERSPEECH.

English Broadcast News Speech Recognition by Humans and Machines

Brian Kingsbury, George Saon, Michael Picheny, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Statistical natural language generation for speech-to-speech machine translation systems

Michael Picheny, Bowen Zhou, Yuqing Gao, 2002, INTERSPEECH.

How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets pdf

Brian Kingsbury, Michael Picheny, Michael Collins, 2014, ArXiv.

Towards Superhuman Speech Recognition

Michael Picheny, David Nahamoo, M. Picheny, 2008 .

Advances in Large Vocabulary Continuous Speech Recognition

Geoffrey Zweig, Michael Picheny, M. Picheny, 2004, Adv. Comput..

Identifying Mood Episodes Using Dialogue Features from Clinical Interviews

Michael Picheny, Emily Mower Provost, Mimansa Jaiswal, 2019, INTERSPEECH.

Articulatory feature detection with Support Vector Machines for integration into ASR and phone recognition

Michael Picheny, Upendra V. Chaudhari, M. Picheny, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

Forget a Bit to Learn Better: Soft Forgetting for CTC-Based Automatic Speech Recognition

Brian Kingsbury, George Saon, Michael Picheny, 2019, INTERSPEECH.

Semantic confidence measurement for spoken dialog systems

Michael Picheny, Ruhi Sarikaya, Hakan Erdogan, 2005, IEEE Transactions on Speech and Audio Processing.

A new confidence measure based on rank-ordering subphone scores

Michael Picheny, Qiguang Lin, Subrata K. Das, 1998, ICSLP.

Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR

Tara N. Sainath, D. Nahamoo, T. N. Sainath, 2011, IEEE Transactions on Audio, Speech, and Language Processing.

Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings

Michael Picheny, Frank Zhang, Yatharth Saraf, 2021, 2110.03520.

Improving Efficiency in Large-Scale Decentralized Distributed Training

Brian Kingsbury, George Saon, Michael Picheny, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improvements in phone based audio search via constrained match with high order confusion estimates

Michael Picheny, Upendra V. Chaudhari, M. Picheny, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

Twenty-Five Years of Evolution in Speech and Language Processing

Dilek Z. Hakkani-Tür, Abdel-rahman Mohamed, M. Picheny, 2023, IEEE Signal Processing Magazine.

Supporting access to large digital oral history archives

Bhuvana Ramabhadran, Michael Picheny, William J. Byrne, 2002, JCDL '02.

A corpus-based approach to expressive speech synthesis

Michael Picheny, Raimo Bakis, John F. Pitrelli, 2004, SSW.

Use of articulatory signals in automatic speech recognition

Louis D. Braida, J. S. Perkell, M. A. Picheny, 1986 .

System combination and score normalization for spoken term detection

Xiaodong Cui, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.