Hynek Hermansky

According to our database, Hynek Hermansky authored at least 244 papers between 1983 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

Self-supervised Learning with Speech Modulation Dropout.

Samik Sadhu, Hynek Hermansky

CoRR, 2023

Stabilized training of joint energy-based models and their practical applications.

Martin Sustek, Samik Sadhu, Lukás Burget, Hynek Hermansky, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak

CoRR, 2023

Importance of Different Temporal Modulations of Speech: a Tale of two Perspectives.

Samik Sadhu, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Blind Signal Dereverberation for Machine Speech Recognition.

Samik Sadhu, Hynek Hermansky

CoRR, 2022

Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition.

Martin Sustek, Samik Sadhu, Hynek Hermansky

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Complex Frequency Domain Linear Prediction: A Tool to Compute Modulation Spectrum of Speech.

Samik Sadhu, Hynek Hermansky

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2021

Two-Stage Augmentation and Adaptive CTC Fusion for Improved Robustness of Multi-Stream end-to-end ASR.

Ruizhi Li, Gregory Sell, Hynek Hermansky

Proceedings of the IEEE Spoken Language Technology Workshop, 2021

Radically Old Way of Computing Spectra: Applications in End-to-End ASR.

Samik Sadhu, Hynek Hermansky

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

2020

Multi-Stream End-to-End Speech Recognition.

Ruizhi Li, Xiaofei Wang, Sri Harish Mallidi, Shinji Watanabe, Takaaki Hori, Hynek Hermansky

IEEE ACM Trans. Audio Speech Lang. Process., 2020

Continual Learning in Automatic Speech Recognition.

Samik Sadhu, Hynek Hermansky

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

An Alternative to MFCCs for ASR.

Pegah Ghahramani, Hossein Hadian, Daniel Povey, Hynek Hermansky, Sanjeev Khudanpur

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

A Practical Two-Stage Training Strategy for Multi-Stream End-to-End Speech Recognition.

Ruizhi Li, Gregory Sell, Xiaofei Wang, Shinji Watanabe, Hynek Hermansky

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

DNN-based performance measures for predicting error rates in automatic speech recognition and optimizing hearing aid parameters.

Angel Mario Castro Martinez, Lukas Gerlach, Guillermo Payá Vayá, Hynek Hermansky, Jasper Ooster, Bernd T. Meyer

Speech Commun., 2019

Coding and decoding of messages in human speech communication: Implications for machine recognition of speech.

Hynek Hermansky

Speech Commun., 2019

Exploring Methods for the Automatic Detection of Errors in Manual Transcription.

Xiaofei Wang, Jinyi Yang, Ruizhi Li, Samik Sadhu, Hynek Hermansky

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Modulation Vectors as Robust Feature Representation for ASR in Domain Mismatched Conditions.

Samik Sadhu, Hynek Hermansky

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Performance Monitoring for End-to-End Speech Recognition.

Ruizhi Li, Gregory Sell, Hynek Hermansky

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Towards Automatic Methods to Detect Errors in Transcriptions of Speech Recordings.

Jinyi Yang, Lucas Ondel, Vimal Manohar, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2019

Stream Attention-based Multi-array End-to-end Speech Recognition.

Xiaofei Wang, Ruizhi Li, Sri Harish Mallidi, Takaaki Hori, Shinji Watanabe, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2019

M-vectors: Sub-band Based Energy Modulation Features for Multi-stream Automatic Speech Recognition.

Samik Sadhu, Ruizhi Li, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2019

Deriving Spectro-temporal Properties of Hearing from Speech Data.

Lucas Ondel, Ruizhi Li, Gregory Sell, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

Multi-encoder multi-resolution framework for end-to-end speech recognition.

Ruizhi Li, Xiaofei Wang, Sri Harish Reddy Mallidi, Takaaki Hori, Shinji Watanabe, Hynek Hermansky

CoRR, 2018

Stream Attention for Distributed Multi-Microphone Speech Recognition.

Xiaofei Wang, Ruizhi Li, Hynek Hermansky

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

2017

Stream Attention for far-field multi-microphone ASR.

Xiaofei Wang, Yonghong Yan, Hynek Hermansky

CoRR, 2017

Predicting error rates for unknown data in automatic speech recognition.

Bernd T. Meyer, Sri Harish Reddy Mallidi, Hendrik Kayser, Hynek Hermansky

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Performance monitoring for automatic speech recognition in noisy multi-channel environments.

Bernd T. Meyer, Sri Harish Reddy Mallidi, Angel Mario Castro Martinez, Guillermo Payá Vayá, Hendrik Kayser, Hynek Hermansky

Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Assessing Speech Quality in Speech-Aware Hearing Aids Based on Phoneme Posteriorgrams.

Constantin Spille, Hendrik Kayser, Hynek Hermansky, Bernd T. Meyer

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

A Framework for Practical Multistream ASR.

Sri Harish Reddy Mallidi, Hynek Hermansky

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

A new efficient measure for accuracy prediction and its application to multistream-based unsupervised adaptation.

Tetsuji Ogawa, Sri Harish Reddy Mallidi, Emmanuel Dupoux, Jordan Cohen, Naomi H. Feldman, Hynek Hermansky

Proceedings of the 23rd International Conference on Pattern Recognition, 2016

Novel neural network based fusion for multistream ASR.

Sri Harish Reddy Mallidi, Hynek Hermansky

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

DNN derived filters for processing of modulation spectrum of speech.

Jan Pesán, Lukás Burget, Hynek Hermansky, Karel Veselý

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Autoencoder based multi-stream combination for noise robust speech recognition.

Sri Harish Reddy Mallidi, Tetsuji Ogawa, Karel Veselý, Phani S. Nidadavolu, Hynek Hermansky

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek Memorial Workshop.

Hynek Hermansky, Lukás Burget, Jordan Cohen, Emmanuel Dupoux, Naomi Feldman, John Godfrey, Sanjeev Khudanpur, Matthew Maciejewski, Sri Harish Reddy Mallidi, Anjali Menon, Tetsuji Ogawa, Vijayaditya Peddinti, Richard C. Rose, Richard M. Stern, Matthew Wiesner, Karel Veselý

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Uncertainty estimation of DNN classifiers.

Sri Harish Reddy Mallidi, Tetsuji Ogawa, Hynek Hermansky

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

Robust speech recognition in unknown reverberant and noisy conditions.

Roger Hsiao, Jeff Z. Ma, William Hartmann, Martin Karafiát, Frantisek Grézl, Lukás Burget, Igor Szöke, Jan Cernocký, Shinji Watanabe, Zhuo Chen, Sri Harish Reddy Mallidi, Hynek Hermansky, Stavros Tsakalidis, Richard M. Schwartz

Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2014

Robust Feature Extraction Using Modulation Filtering of Autoregressive Models.

Sriram Ganapathy, Sri Harish Reddy Mallidi, Hynek Hermansky

IEEE ACM Trans. Audio Speech Lang. Process., 2014

Evaluating speech features with the minimal-pair ABX task (II): resistance to noise.

Thomas Schatz, Vijayaditya Peddinti, Xuan-Nga Cao, Francis R. Bach, Hynek Hermansky, Emmanuel Dupoux

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Principal components of auditory spectro-temporal receptive fields.

Nagaraj Mahajan, Nima Mesgarani, Hynek Hermansky

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

A long, deep and wide artificial neural net for robust speech recognition in unknown noise.

Feipeng Li, Phani S. Nidadavolu, Hynek Hermansky

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Featherweight phonetic keyword search for conversational speech.

Keith Kintzley, Aren Jansen, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

Factor Analysis of Auto-Associative Neural Networks With Application in Speaker Verification.

Sri Garimella, Hynek Hermansky

IEEE Trans. Neural Networks Learn. Syst., 2013

Perceptual Properties of Current Speech Recognition Technology.

Hynek Hermansky, Jordan R. Cohen, Richard M. Stern

Proc. IEEE, 2013

Multistream Recognition of Speech: Dealing With Unknown Unknowns.

Hynek Hermansky

Proc. IEEE, 2013

Long, Deep and Wide Artificial Neural Nets for Dealing with Unexpected Noise in Machine Recognition of Speech.

Hynek Hermansky

Proceedings of the Text, Speech, and Dialogue - 16th International Conference, 2013

Multi-stream recognition of noisy speech with performance monitoring.

Ehsan Variani, Feipeng Li, Hynek Hermansky

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Evaluating speech features with the minimal-pair ABX task: analysis of the classical MFC/PLP pipeline.

Thomas Schatz, Vijayaditya Peddinti, Francis R. Bach, Aren Jansen, Hynek Hermansky, Emmanuel Dupoux

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Stream selection and integration in multistream ASR using GMM-based performance monitoring.

Tetsuji Ogawa, Feipeng Li, Hynek Hermansky

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Robust speaker recognition using spectro-temporal autoregressive models.

Sri Harish Reddy Mallidi, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Improvements in language identification on the RATS noisy speech corpus.

Jeff Z. Ma, Bing Zhang, Spyros Matsoukas, Sri Harish Reddy Mallidi, Feipeng Li, Hynek Hermansky

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Text-to-speech inspired duration modeling for improved whole-word acoustic models.

Keith Kintzley, Aren Jansen, Hynek Hermansky

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Deep neural network features and semi-supervised training for low resource speech recognition.

Samuel Thomas, Michael L. Seltzer, Kenneth Church, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2013

Developing a speaker identification system for the DARPA RATS project.

Oldrich Plchot, Spyros Matsoukas, Pavel Matejka, Najim Dehak, Jeff Z. Ma, Sandro Cumani, Ondrej Glembek, Hynek Hermansky, Sri Harish Reddy Mallidi, Nima Mesgarani, Richard M. Schwartz, Mehdi Soufifar, Zheng-Hua Tan, Samuel Thomas, Bing Zhang, Xinhui Zhou

Proceedings of the IEEE International Conference on Acoustics, 2013

Filter-bank optimization for Frequency Domain Linear Prediction.

Vijayaditya Peddinti, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2013

Effect of filter bandwidth and spectral sampling rate of analysis filterbank on automatic phoneme recognition.

Feipeng Li, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2013

Weak top-down constraints for unsupervised acoustic model training.

Aren Jansen, Samuel Thomas, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2013

A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition.

Aren Jansen, Emmanuel Dupoux, Sharon Goldwater, Mark Johnson, Sanjeev Khudanpur, Kenneth Church, Naomi Feldman, Hynek Hermansky, Florian Metze, Richard C. Rose, Mike Seltzer, Pascal Clark, Ian McGraw, Balakrishnan Varadarajan, Erin Bennett, Benjamin Börschinger, Justin T. Chiu, Ewan Dunbar, Abdellah Fourtassi, David Harwath, Chia-ying Lee, Keith D. Levin, Atta Norouzian, Vijayaditya Peddinti, Rachael Richardson, Thomas Schatz, Samuel Thomas

Proceedings of the IEEE International Conference on Acoustics, 2013

Mean temporal distance: Predicting ASR error from temporal properties of speech signal.

Hynek Hermansky, Ehsan Variani, Vijayaditya Peddinti

Proceedings of the IEEE International Conference on Acoustics, 2013

Frequency offset correction in speech without detecting pitch.

Pascal Clark, Sri Harish Reddy Mallidi, Aren Jansen, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2013

2012

DIRAC: Detection and Identification of Rare Audio-Visual Events.

Jörn Anemüller, Barbara Caputo, Hynek Hermansky, Frank W. Ohl, Tomás Pajdla, Misha Pavel, Luc Van Gool, Rufin Vogels, Stefan Wabnik, Daphna Weinshall

Proceedings of the Detection and Identification of Rare Audiovisual Cues, 2012

Sparse Multilayer Perceptron for Phoneme Recognition.

Garimella S. V. S. Sivaram, Hynek Hermansky

IEEE Trans. Speech Audio Process., 2012

Regularized Auto-Associative Neural Networks for Speaker Verification.

Sri Garimella, Sri Harish Reddy Mallidi, Hynek Hermansky

IEEE Signal Process. Lett., 2012

Phase AutoCorrelation (PAC) features for noise robust speech recognition.

Shajith Ikbal, Hemant Misra, Hynek Hermansky, Mathew Magimai-Doss

Speech Commun., 2012

Beyond Novelty Detection: Incongruent Events, When General and Specific Classifiers Disagree.

Daphna Weinshall, Alon Zweig, Hynek Hermansky, Stefan Kombrink, Frank W. Ohl, Jörn Anemüller, Jörg-Hendrik Bach, Luc Van Gool, Fabian Nater, Tomás Pajdla, Michal Havlena, Misha Pavel

IEEE Trans. Pattern Anal. Mach. Intell., 2012

Adaptation transforms of auto-associative neural networks as features for speaker verification.

Samuel Thomas, Sri Harish Reddy Mallidi, Sriram Ganapathy, Hynek Hermansky

Proceedings of the Odyssey 2012: The Speaker and Language Recognition Workshop, 2012

Factor analysis of mixture of auto-associative neural networks for speaker verification.

Sri Garimella, Hynek Hermansky

Proceedings of the Odyssey 2012: The Speaker and Language Recognition Workshop, 2012

Feature extraction using 2-d autoregressive models for speaker recognition.

Sriram Ganapathy, Samuel Thomas, Hynek Hermansky

Proceedings of the Odyssey 2012: The Speaker and Language Recognition Workshop, 2012

Estimating Classifier Performance in Unknown Noise.

Ehsan Variani, Hynek Hermansky

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Acoustic and Data-driven Features for Robust Speech Activity Detection.

Samuel Thomas, Sri Harish Reddy Mallidi, Thomas Janu, Hynek Hermansky, Nima Mesgarani, Xinhui Zhou, Shihab A. Shamma, Tim Ng, Bing Zhang, Long Nguyen, Spyros Matsoukas

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Data-driven Posterior Features for Low Resource Speech Recognition Applications.

Samuel Thomas, Sriram Ganapathy, Aren Jansen, Hynek Hermansky

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Phone recognition in critical bands using sub-band temporal modulations.

Feipeng Li, Sri Harish Reddy Mallidi, Hynek Hermansky

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

MAP Estimation of Whole-Word Acoustic Models with Dictionary Priors.

Keith Kintzley, Aren Jansen, Hynek Hermansky

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Inverting the Point Process Model for Fast Phonetic Keyword Search.

Keith Kintzley, Aren Jansen, Kenneth Church, Hynek Hermansky

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Intrinsic Spectral Analysis for Zero and High Resource Speech Recognition.

Aren Jansen, Samuel Thomas, Hynek Hermansky

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Analysis of Temporal Resolution in Frequency Domain Linear Prediction.

Sriram Ganapathy, Hynek Hermansky

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Multilingual MLP features for low-resource LVCSR systems.

Samuel Thomas, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

The UMD-JHU 2011 speaker recognition system.

Daniel Garcia-Romero, Xinhui Zhou, Dmitry N. Zotkin, Balaji Vasan Srinivasan, Yuancheng Luo, Sriram Ganapathy, Samuel Thomas, Sridhar Krishna Nemala, Garimella S. V. S. Sivaram, Majid Mirbagheri, Sri Harish Reddy Mallidi, Thomas Janu, Padmanabhan Rajan, Nima Mesgarani, Mounya Elhilali, Hynek Hermansky, Shihab A. Shamma, Ramani Duraiswami

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Comparison of Different Approaches for Speech Recognition in Hands-free Mode.

Hans-Günter Hirsch, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 10th ITG Conference on Speech Communication, 2012

2011

Analysis of MLP-Based Hierarchical Phoneme Posterior Probability Estimator.

Joel Pinto, Garimella S. V. S. Sivaram, Mathew Magimai-Doss, Hynek Hermansky, Hervé Bourlard

IEEE Trans. Speech Audio Process., 2011

Multi-layer perceptron based speech activity detection for speaker verification.

Sriram Ganapathy, Padmanabhan Rajan, Hynek Hermansky

Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2011

Dealing with Unexpected Words in Automatic Recognition of Speech.

Hynek Hermansky

Proceedings of the Text, Speech and Dialogue - 14th International Conference, 2011

Performance monitoring for robustness in automatic recognition of speechi.

Hynek Hermansky, Nima Mesgarani, Samuel Thomas

Proceedings of the 2011 Symposium on Machine Learning in Speech and Language Processing, 2011

Mixture of Auto-Associative Neural Networks for Speaker Verification.

Garimella S. V. S. Sivaram, Samuel Thomas, Hynek Hermansky

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Adaptive Stream Fusion in Multistream Recognition of Speech.

Nima Mesgarani, Samuel Thomas, Hynek Hermansky

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Modulation Spectrum Analysis for Recognition of Reverberant Speech.

Sri Harish Reddy Mallidi, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Event Selection from Phone Posteriorgrams Using Matched Filters.

Keith Kintzley, Aren Jansen, Hynek Hermansky

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Rapid Evaluation of Speech Representations for Spoken Term Discovery.

Michael A. Carlin, Samuel Thomas, Aren Jansen, Hynek Hermansky

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Speech recognitionwith segmental conditional random fields: A summary of the JHU CLSP 2010 Summer Workshop.

Geoffrey Zweig, Patrick Nguyen, Dirk Van Compernolle, Kris Demuynck, Les E. Atlas, Pascal Clark, Gregory Sell, Meihong Wang, Fei Sha, Hynek Hermansky, Damianos G. Karakos, Aren Jansen, Samuel Thomas, Sivaram G. S. V. S., Samuel R. Bowman, Justine T. Kao

Proceedings of the IEEE International Conference on Acoustics, 2011

MLP based phoneme detectors for Automatic Speech Recognition.

Samuel Thomas, Patrick Nguyen, Geoffrey Zweig, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2011

Multilayer perceptron with sparse hidden outputs for phoneme recognition.

Garimella S. V. S. Sivaram, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

Autoregressive Models of Amplitude Modulations in Audio Compression.

Sriram Ganapathy, Petr Motlícek, Hynek Hermansky

IEEE Trans. Speech Audio Process., 2010

Data-Driven and Feedback Based Spectro-Temporal Features for Speech Recognition.

Garimella S. V. S. Sivaram, Sridhar Krishna Nemala, Nima Mesgarani, Hynek Hermansky

IEEE Signal Process. Lett., 2010

Wide-Band Audio Coding Based on Frequency-Domain Linear Prediction.

Petr Motlícek, Sriram Ganapathy, Hynek Hermansky, Harinath Garudadri

EURASIP J. Audio Speech Music. Process., 2010

Recovery of Rare Words in Lecture Speech.

Stefan Kombrink, Mirko Hannemann, Lukás Burget, Hynek Hermansky

Proceedings of the Text, Speech and Dialogue, 13th International Conference, 2010

The use of spike-based representations for hardware audition systems.

Shih-Chii Liu, Nima Mesgarani, John G. Harris, Hynek Hermansky

Proceedings of the International Symposium on Circuits and Systems (ISCAS 2010), May 30, 2010

Fully integrated 500uW speech detection wake-up circuit.

Tobi Delbrück, Thomas Koch, Raphael Berner, Hynek Hermansky

Proceedings of the International Symposium on Circuits and Systems (ISCAS 2010), May 30, 2010

A phoneme recognition framework based on auditory spectro-temporal receptive fields.

Samuel Thomas, Kailash Patil, Sriram Ganapathy, Nima Mesgarani, Hynek Hermansky

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Cross-lingual and multi-stream posterior features for low resource LVCSR systems.

Samuel Thomas, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Sparse auto-associative neural networks: theory and application to speech recognition.

Garimella S. V. S. Sivaram, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

A multistream multiresolution framework for phoneme recognition.

Nima Mesgarani, Samuel Thomas, Hynek Hermansky

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Towards spoken term discovery at scale with zero resources.

Aren Jansen, Kenneth Church, Hynek Hermansky

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Sparse coding for speech recognition.

Garimella S. V. S. Sivaram, Sridhar Krishna Nemala, Mounya Elhilali, Trac D. Tran, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2010

History of modulation spectrum in ASR.

Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2010

Comparison of modulation features for phoneme recognition.

Sriram Ganapathy, Samuel Thomas, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2010

Robust spectro-temporal features based on autoregressive models of Hilbert envelopes.

Sriram Ganapathy, Samuel Thomas, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

Intelligent Multi-modal Interfaces for Mobile Applications in Hostile Environment(IM-HOST).

Claude Stricker, Jean-Frédéric Wagen, Guillermo Aradilla, Hervé Bourlard, Hynek Hermansky, Joel Pinto, Paul-Henri Rey, Jérôme Théraulaz

Proceedings of the Human Machine Interaction, Research Results of the MMI Program, 2009

Applications of signal analysis using autoregressive models for amplitude modulation.

Sriram Ganapathy, Samuel Thomas, Petr Motlícek, Hynek Hermansky

Proceedings of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2009

Error Resilient Speech Coding Using Sub-band Hilbert Envelopes.

Sriram Ganapathy, Petr Motlícek, Hynek Hermansky

Proceedings of the Text, Speech and Dialogue, 12th International Conference, 2009

Tandem representations of spectral envelope and modulation frequency features for ASR.

Samuel Thomas, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Arithmetic coding of sub-band residuals in FDLP speech/audio codec.

Petr Motlícek, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Discriminant spectrotemporal features for phoneme recognition.

Nima Mesgarani, Garimella S. V. S. Sivaram, Sridhar Krishna Nemala, Mounya Elhilali, Hynek Hermansky

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Posterior-based out of vocabulary word detection in telephone speech.

Stefan Kombrink, Lukás Burget, Pavel Matejka, Martin Karafiát, Hynek Hermansky

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Static and dynamic modulation spectrum for speech recognition.

Sriram Ganapathy, Samuel Thomas, Hynek Hermansky

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Phoneme recognition using spectral envelope and modulation frequency features.

Samuel Thomas, Sriram Ganapathy, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2009

Volterra series for analyzing MLP based phoneme posterior estimator.

Joel Pinto, Garimella S. V. S. Sivaram, Hynek Hermansky, Mathew Magimai-Doss

Proceedings of the IEEE International Conference on Acoustics, 2009

Reconciliation of human and machine speech recognition performance.

Misha Pavel, Malcolm Slaney, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2009

Temporal envelope subtraction for robust speech recognition using modulation spectrum.

Sriram Ganapathy, Samuel Thomas, Hynek Hermansky

Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 2009

2008

Recognition of Reverberant Speech Using Frequency Domain Linear Prediction.

Samuel Thomas, Sriram Ganapathy, Hynek Hermansky

IEEE Signal Process. Lett., 2008

Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR.

Garimella S. V. S. Sivaram, Hynek Hermansky

Proceedings of the Text, Speech and Dialogue, 11th International Conference, 2008

Reverse Correlation for Analyzing MLP Posterior Features in ASR.

Joel Pinto, Garimella S. V. S. Sivaram, Hynek Hermansky

Proceedings of the Text, Speech and Dialogue, 11th International Conference, 2008

Exploiting Contextual Information for Speech/Non-Speech Detection.

Sree Hari Krishnan Parthasarathi, Petr Motlícek, Hynek Hermansky

Proceedings of the Text, Speech and Dialogue, 11th International Conference, 2008

Perceptually Motivated Sub-band Decomposition for FDLP Audio Coding.

Petr Motlícek, Sriram Ganapathy, Hynek Hermansky, Harinath Garudadri, Marios Athineos

Proceedings of the Text, Speech and Dialogue, 11th International Conference, 2008

Beyond Novelty Detection: Incongruent Events, when General and Specific Classifiers Disagree.

Daphna Weinshall, Hynek Hermansky, Alon Zweig, Jie Luo, Holly Brügge Jimison, Frank W. Ohl, Misha Pavel

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

Hilbert Envelope Based Features for Far-Field Speech Recognition.

Samuel Thomas, Sriram Ganapathy, Hynek Hermansky

Proceedings of the Machine Learning for Multimodal Interaction, 5th International Workshop, 2008

On the combination of auditory and modulation frequency channels for ASR applications.

Fabio Valente, Hynek Hermansky

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Hilbert envelope based spectro-temporal features for phoneme recognition in telephone speech.

Samuel Thomas, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Introducing temporal asymmetries in feature extraction for automatic speech recognition.

Garimella S. V. S. Sivaram, Hynek Hermansky

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Combining evidence from a generative and a discriminative model in phoneme recognition.

Joel Pinto, Hynek Hermansky

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Front-end for far-field speech recognition based on frequency domain linear prediction.

Sriram Ganapathy, Samuel Thomas, Hynek Hermansky

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Spectral noise shaping: improvements in speech/audio codec based on linear prediction in spectral domain.

Sriram Ganapathy, Petr Motlícek, Hynek Hermansky, Harinath Garudadri

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

The DIRAC AWEAR audio-visual platform for detection of unexpected and incongruent events.

Jörn Anemüller, Jörg-Hendrik Bach, Barbara Caputo, Michal Havlena, Jie Luo, Hendrik Kayser, Bastian Leibe, Petr Motlícek, Tomás Pajdla, Misha Pavel, Akihiko Torii, Luc Van Gool, Alon Zweig, Hynek Hermansky

Proceedings of the 10th International Conference on Multimodal Interfaces, 2008

Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments.

Christopher M. White, Geoffrey Zweig, Lukás Burget, Petr Schwarz, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2008

Hierarchical and parallel processing of modulation spectrum for ASR applications.

Fabio Valente, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2008

Exploiting contextual information for improved phoneme recognition.

Joel Pinto, B. Yegnanarayana, Hynek Hermansky, Mathew Magimai-Doss

Proceedings of the IEEE International Conference on Acoustics, 2008

Temporal masking for bit-rate reduction in audio codec based on Frequency Domain Linear Prediction.

Sriram Ganapathy, Petr Motlícek, Hynek Hermansky, Harinath Garudadri

Proceedings of the IEEE International Conference on Acoustics, 2008

Combination of strongly and weakly constrained recognizers for reliable detection of OOVS.

Lukás Burget, Petr Schwarz, Pavel Matejka, Mirko Hannemann, Ariya Rastrow, Christopher M. White, Sanjeev Khudanpur, Hynek Hermansky, Jan Cernocký

Proceedings of the IEEE International Conference on Acoustics, 2008

Using comparison of parallel phoneme probability streams for OOV word detection.

Tamara Tosic, Mathew Magimai-Doss, Hynek Hermansky

Proceedings of the 2008 16th European Signal Processing Conference, 2008

Spectro-temporal features for Automatic Speech Recognition using Linear Prediction in spectral domain.

Samuel Thomas, Sriram Ganapathy, Hynek Hermansky

Proceedings of the 2008 16th European Signal Processing Conference, 2008

Emulating temporal receptive fields of auditory mid-brain neurons for automatic speech recognition.

Garimella S. V. S. Sivaram, Hynek Hermansky

Proceedings of the 2008 16th European Signal Processing Conference, 2008

2007

Non-uniform Speech/Audio Coding Exploiting Predictability of Temporal Evolution of Spectral Envelopes.

Petr Motlícek, Hynek Hermansky, Sriram Ganapathy, Harinath Garudadri

Proceedings of the Text, Speech and Dialogue, 10th International Conference, 2007

Frequency Domain Linear Prediction for QMF Sub-bands and Applications to Audio Coding.

Petr Motlícek, Sriram Ganapathy, Hynek Hermansky, Harinath Garudadri

Proceedings of the Machine Learning for Multimodal Interaction , 2007

Hierarchical neural networks feature extraction for LVCSR system.

Fabio Valente, Jithendra Vepa, Christian Plahl, Christian Gollan, Hynek Hermansky, Ralf Schlüter

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Multi-stream features combination based on dempster-shafer rule for LVCSR system.

Fabio Valente, Jithendra Vepa, Hynek Hermansky

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

MRASTA and PLP in automatic speech recognition.

S. R. Mahadeva Prasanna, Hynek Hermansky

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Exploiting phoneme similarities in hybrid HMM-ANN keyword spotting.

Joel Pinto, Andrew Lovitt, Hynek Hermansky

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Detection of out-of-vocabulary words in posterior based ASR.

Hamed Ketabdar, Mirko Hannemann, Hynek Hermansky

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Combination of Acoustic Classifiers Based on Dempster-Shafer Theory of Evidence.

Fabio Valente, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2007

Wide-Band Perceptual Audio Coding Based on Frequency-Domain Linear Prediction.

Petr Motlícek, Vijay Ullal, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2007

2006

Speech Coding Based on Spectral Dynamics.

Petr Motlícek, Hynek Hermansky, Harinath Garudadri, Naveen Srinivasamurthy

Proceedings of the Text, Speech and Dialogue, 9th International Conference, 2006

Discriminant linear processing of time-frequency plane.

Fabio Valente, Hynek Hermansky

Proceedings of the Ninth International Conference on Spoken Language Processing, 2006

Towards ASR Based on Hierarchical Posterior-Based Keyword Recognition.

Petr Fousek, Hynek Hermansky

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005

Pushing the envelope - aside [speech recognition].

Nelson Morgan, Qifeng Zhu, Andreas Stolcke, M. Kemal Sönmez, Sunil Sivadas, Takahiro Shinozaki, Mari Ostendorf, Pratibha Jain, Hynek Hermansky, Dan Ellis, George R. Doddington, Barry Y. Chen, Özgür Çetin, Hervé Bourlard, Marios Athineos

IEEE Signal Process. Mag., 2005

Editorial.

Werner Verhelst, Jürgen Herre, Gernot Kubin, Hynek Hermansky, Søren Holdt Jensen

EURASIP J. Adv. Signal Process., 2005

The Role of Speech in Multimodal Human-Computer Interaction.

Hynek Hermansky, Petr Fousek, Mikko Lehtonen

Proceedings of the Text, Speech and Dialogue, 8th International Conference, 2005

Multi-resolution RASTA filtering for TANDEM-based ASR.

Hynek Hermansky, Petr Fousek

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

2004

Entropy based combination of tandem representations for noise robust ASR.

Shajith Ikbal, Hemant Misra, Sunil Sivadas, Hynek Hermansky, Hervé Bourlard

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Stochastic techniques in deriving perceptual knowledge.

Hynek Hermansky

Proceedings of the ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing, 2004

New nonsense syllables database - analyses and preliminary ASR experiments.

Petr Fousek, Frantisek Grézl, Hynek Hermansky, Petr Svojanovsky

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

PLP-squared: autoregressive modeling of auditory-like 2-d spectro-temporal patterns.

Marios Athineos, Hynek Hermansky, Daniel P. W. Ellis

Proceedings of the ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing, 2004

LP-TRAP: linear predictive temporal patterns.

Marios Athineos, Hynek Hermansky, Daniel P. W. Ellis

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

On use of task independent training data in tandem feature extraction.

Sunil Sivadas, Hynek Hermansky

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Spectral entropy based feature for robust ASR.

Hemant Misra, Shajith Ikbal, Hervé Bourlard, Hynek Hermansky

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Phase autocorrelation (PAC) features in entropy based multi-stream for robust speech recognition.

Shajith Ikbal, Hemant Misra, Hervé Bourlard, Hynek Hermansky

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003

Data-driven spectral basis functions for automatic speech recognition.

Naren Malayath, Hynek Hermansky

Speech Commun., 2003

Phoneme Recognition Using Temporal Patterns.

Pavel Matejka, Petr Schwarz, Hynek Hermansky, Jan Cernocký

Proceedings of the Text, Speech and Dialogue, 6th International Conference, 2003

In search of target class definition in tandem feature extraction.

Sunil Sivadas, Hynek Hermansky

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Novel approaches for one- and two-speaker detection.

Sachin S. Kajarekar, André Gustavo Adami, Hynek Hermansky

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Beyond a single critical-band in TRAP based ASR.

Pratibha Jain, Hynek Hermansky

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Band-independent speech-event categories for TRAP based ASR.

Hynek Hermansky, Pratibha Jain

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Local averaging and differentiating of spectral plane for TRAP-based ASR.

Frantisek Grézl, Hynek Hermansky

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Segmentation of speech for speaker and language recognition.

André Gustavo Adami, Hynek Hermansky

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Generalized tandem feature extraction.

Sunil Sivadas, Hynek Hermansky

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002

Analysis of Information in Speech Based on MANOVA.

Sachin S. Kajarekar, Hynek Hermansky

Proceedings of the Advances in Neural Information Processing Systems 15 [Neural Information Processing Systems, 2002

Bark resolution from speech data.

Naren Malayath, Hynek Hermansky

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Distributed speech recognition using noise-robust MFCC and traps-estimated manner features.

Pratibha Jain, Hynek Hermansky, Brian Kingsbury

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Qualcomm-ICSI-OGI features for ASR.

André Gustavo Adami, Lukás Burget, Stéphane Dupont, Harinath Garudadri, Frantisek Grézl, Hynek Hermansky, Pratibha Jain, Sachin S. Kajarekar, Nelson Morgan, Sunil Sivadas

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Hierarchical tandem feature extraction.

Sunil Sivadas, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2002

A new speaker change detection method for two-speaker segmentation.

André Gustavo Adami, Sachin S. Kajarekar, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2002

2001

Human Speech Perception: Some Lessons from Automatic Speech Recognition.

Hynek Hermansky

Proceedings of the Text, Speech and Dialogue, 4th International Conference, 2001

Data Driven Design of Filter Bank for Speech Recognition.

Lukás Burget, Hynek Hermansky

Proceedings of the Text, Speech and Dialogue, 4th International Conference, 2001

Speaker verification based on broad phonetic categories.

Sachin S. Kajarekar, Hynek Hermansky

Proceedings of the 2001: A Speaker Odyssey, 2001

Robust ASR front-end using spectral-based and discriminant features: experiments on the Aurora tasks.

M. Carmen Benítez, Lukás Burget, Barry Y. Chen, Stéphane Dupont, Harinath Garudadri, Hynek Hermansky, Pratibha Jain, Sachin S. Kajarekar, Nelson Morgan, Sunil Sivadas

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

A study of two dimensional linear discriminants for ASR.

Sachin S. Kajarekar, Bayya Yegnanarayana, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2001

2000

Relevance of time-frequency features for phonetic and speaker-channel classification.

Howard Hua Yang, Sarel van Vuuren, Sangita Sharma, Hynek Hermansky

Speech Commun., 2000

Data-Driven Temporal Filters and Alternatives to GMM in Speaker Verification.

Naren Malayath, Hynek Hermansky, Sachin S. Kajarekar, B. Yegnanarayana

Digit. Signal Process., 2000

Analysis of Information in Speech and Its Application in Speech Recognition.

Sachin S. Kajarekar, Hynek Hermansky

Proceedings of the Text, Speech and Dialogue - Third International Workshop, 2000

Discriminative MLPs in HMM-based recognition of speech in cellular telephony.

Sunil Sivadas, Pratibha Jain, Hynek Hermansky

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Optimization of units for continuous-digit recognition task.

Sachin S. Kajarekar, Hynek Hermansky

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Temporal patterns of critical-band spectrum for text-to-speech.

Pratibha Jain, Hynek Hermansky

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Feature extraction using non-linear transformation for robust speech recognition on the Aurora database.

Sangita Sharma, Dan Ellis, Sachin S. Kajarekar, Pratibha Jain, Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 2000

Tandem connectionist feature extraction for conventional HMM systems.

Hynek Hermansky, Daniel P. W. Ellis, Sangita Sharma

Proceedings of the IEEE International Conference on Acoustics, 2000

1999

Speech enhancement using linear prediction residual.

B. Yegnanarayana, Carlos Avendaño, Hynek Hermansky, P. Satyanarayana Murthy

Speech Commun., 1999

On the relative importance of various components of the modulation spectrum for automatic speech recognition.

Noboru Kanedera, Takayuki Arai, Hynek Hermansky, Misha Pavel

Speech Commun., 1999

Data-Driven Analysis of Speech.

Hynek Hermansky

Proceedings of the Text, Speech and Dialogue - Second International Workshop, 1999

Search for Information Bearing Components in Speech.

Howard Hua Yang, Hynek Hermansky

Proceedings of the Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29, 1999

The purpose, history, current state, and some evolving trends in feature extraction for speech recognition.

Hynek Hermansky

Proceedings of the ISSPA '99. Proceedings of the Fifth International Symposium on Signal Processing and its Applications, 1999

Speech variability in the modulation spectral domain - SANOVA technique -.

Sarel van Vuuren, Hynek Hermansky

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Analysis of sources of variability in speech.

Sachin S. Kajarekar, Narendranath Malayath, Hynek Hermansky

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Down-sampling speech representation in ASR.

Hynek Hermansky, Pratibha Jain

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Relevancy of time-frequency features for phonetic classification measured by mutual information.

Howard Hua Yang, Sarel van Vuuren, Hynek Hermansky

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

Temporal patterns (TRAPs) in ASR of noisy speech.

Hynek Hermansky, Sangita Sharma

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

1998

Should recognizers have ears?

Hynek Hermansky

Speech Commun., 1998

On the importance of components of the modulation spectrum for speaker verification.

Sarel van Vuuren, Hynek Hermansky

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

TRAPS - classifiers of temporal patterns.

Hynek Hermansky, Sangita Sharma

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Spectral basis functions from discriminant analysis.

Hynek Hermansky, Narendranath Malayath

Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Enhancement of reverberant speech using LP residual.

B. Yegnanarayana, P. Satyanarayana Murthy, Carlos Avendaño, Hynek Hermansky

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

On properties of modulation spectrum for robust automatic speech recognition.

Noboru Kanedera, Hynek Hermansky, Takayuki Arai

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

1997

On the effects of short-term spectrum smoothing in channel normalization.

Carlos Avendaño, Hynek Hermansky

IEEE Trans. Speech Audio Process., 1997

Processing linear prediction residual for speech enhancement.

B. Yegnanarayana, Carlos Avendaño, Hynek Hermansky, P. Satyanarayana Murthy

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Data-driven design of RASTA-like filters.

Sarel van Vuuren, Hynek Hermansky

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Multi-band and adaptation approaches to robust speech recognition.

Sangita Tibrewala, Hynek Hermansky

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Towards decomposing the sources of variability in speech.

Narendranath Malayath, Hynek Hermansky, Alexander Kain

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

On the importance of various modulation frequencies for speech recognition.

Noboru Kanedera, Takayuki Arai, Hynek Hermansky, Misha Pavel

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Multiresolution channel normalization for ASR in reverberant environments.

Carlos Avendaño, Sangita Tibrewala, Hynek Hermansky

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Sub-band based recognition of noisy speech.

Sangita Tibrewala, Hynek Hermansky

Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

1996

Towards increasing speech recognition error rates.

Hervé Bourlard, Hynek Hermansky, Nelson Morgan

Speech Commun., 1996

Towards ASR on partially corrupted speech.

Hynek Hermansky, Sangita Tibrewala, Misha Pavel

Proceedings of the 4th International Conference on Spoken Language Processing, 1996

Data based filter design for RASTA-like channel normalization in ASR.

Carlos Avendaño, Sarel van Vuuren, Hynek Hermansky

Proceedings of the 4th International Conference on Spoken Language Processing, 1996

Study on the dereverberation of speech based on temporal envelope filtering.

Carlos Avendaño, Hynek Hermansky

Proceedings of the 4th International Conference on Spoken Language Processing, 1996

Intelligibility of speech with filtered time trajectories of spectral envelopes.

Takayuki Arai, Misha Pavel, Hynek Hermansky, Carlos Avendaño

Proceedings of the 4th International Conference on Spoken Language Processing, 1996

Towards subband-based speech recognition.

Hervé Bourlard, Stéphane Dupont, Hynek Hermansky, Nelson Morgan

Proceedings of the 8th European Signal Processing Conference, 1996

1995

The challenge of spoken language systems: research directions for the nineties.

Ronald A. Cole, Lynette Hirschman, Les E. Atlas, Mary E. Beckman, Alan Biermann, Marcia A. Bush, Mark Clements, Jordan Cohen, Oscar Garcia, Brian A. Hanson, Hynek Hermansky, Steve Levinson, Kathy McKeown, Nelson Morgan, David G. Novick, Mari Ostendorf, Sharon L. Oviatt, Patti Price, Harvey F. Silverman, Judy Spitz, Alex Waibel, Clifford J. Weinstein, Stephen A. Zahorian, Victor Zue

IEEE Trans. Speech Audio Process., 1995

Beyond NYQUIST: towards the recovery of broad-bandwidth speech from narrow-bandwidth speech.

Carlos Avendaño, Hynek Hermansky, Eric A. Wan

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

Stochastic perceptual models of speech.

Nelson Morgan, Hervé Bourlard, Steven Greenberg, Hynek Hermansky, Su-Lin Wu

Proceedings of the 1995 International Conference on Acoustics, 1995

Speech enhancement based on temporal processing.

Hynek Hermansky, Eric A. Wan, Carlos Avendaño

Proceedings of the 1995 International Conference on Acoustics, 1995

1994

RASTA processing of speech.

Hynek Hermansky, Nelson Morgan

IEEE Trans. Speech Audio Process., 1994

Stochastic perceptual auditory-event-based models for speech recognition.

Nelson Morgan, Hervé Bourlard, Steven Greenberg, Hynek Hermansky

Proceedings of the 3rd International Conference on Spoken Language Processing, 1994

Integrating RASTA-PLP into speech recognition.

Joachim Koehler, Nelson Morgan, Hynek Hermansky, Hans-Günter Hirsch, Grace Tong

Proceedings of ICASSP '94: IEEE International Conference on Acoustics, 1994

1993

Evaluation and optimization of perceptually-based ASR front-end.

Jean-Claude Junqua, Hisashi Wakita, Hynek Hermansky

IEEE Trans. Speech Audio Process., 1993

Recognition of speech in additive and convolutional noise based on RASTA spectral processing.

Hynek Hermansky, Nelson Morgan, Hans-Günter Hirsch

Proceedings of the IEEE International Conference on Acoustics, 1993

1992

Towards handling the acoustic environment in spoken language processing.

Hynek Hermansky, Nelson Morgan

Proceedings of the Second International Conference on Spoken Language Processing, 1992

RASTA-PLP speech analysis technique.

Hynek Hermansky, Nelson Morgan, Aruna Bayya, Phil Kohn

Proceedings of the 1992 IEEE International Conference on Acoustics, 1992

1991

Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP).

Hynek Hermansky, Nelson Morgan, Aruna Bayya, Phil Kohn

Proceedings of the Second European Conference on Speech Communication and Technology, 1991

Perceptual linear predictive (PLP) analysis-resynthesis technique.

Hynek Hermansky, Louis Anthony Cox Jr.

Proceedings of the Second European Conference on Speech Communication and Technology, 1991

Continuous speech recognition using PLP analysis with multilayer perceptrons.

Nelson Morgan, Hynek Hermansky, Hervé Bourlard, Phil Kohn, Chuck Wooters

Proceedings of the 1991 International Conference on Acoustics, 1991

1990

Towards feature-based speech metric.

Aruna Bayya, Hynek Hermansky

Proceedings of the 1990 International Conference on Acoustics, 1990

1989

The effective second formant F2' and the vocal tract front-cavity.

Hynek Hermansky, David J. Broad

Proceedings of the IEEE International Conference on Acoustics, 1989

1988

Optimization of perceptually-based ASR front-end [automatic speech recognition].

Hynek Hermansky, Jean-Claude Junqua

Proceedings of the IEEE International Conference on Acoustics, 1988

1987

Automatic speech recognition and human auditory perception.

Hynek Hermansky

Proceedings of the European Conference on Speech Technology, 1987

An efficient speaker-independent automatic speech recognition by simulation of some properties of human auditory perception.

Hynek Hermansky

Proceedings of the IEEE International Conference on Acoustics, 1987

1986

Perceptually based processing in automatic speech recognition.

Hynek Hermansky, Kazuhiro Tsuga, Shozo Makino, Hisashi Wakita

Proceedings of the IEEE International Conference on Acoustics, 1986

1985

Low-dimensional representation of vowels based on all-pole modeling in the psychophysical domain.

Hynek Hermansky, Brian A. Hanson, Hisashi Wakita

Speech Commun., 1985

Perceptually based linear predictive analysis of speech.

Hynek Hermansky, Brian A. Hanson, Hisashi Wakita

Proceedings of the IEEE International Conference on Acoustics, 1985

1984

Spectral envelope sampling and interpolation in linear predictive analysis of speech.

Hynek Hermansky, Hiroya Fujisaki, Yasuo Sato

Proceedings of the IEEE International Conference on Acoustics, 1984

1983

Analysis and synthesis of speech based on spectral transform linear predictive method.

Hynek Hermansky, Hiroya Fujisaki, Yasuo Sato

Proceedings of the IEEE International Conference on Acoustics, 1983