Daniel Povey

发表

Speaker adaptation with an Exponential Transform

Geoffrey Zweig, Daniel Povey, Alex Acero, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Morpheme-Based Language Modeling for Arabic Lvcsr

Geoffrey Zweig, Daniel Povey, Ghinwa F. Choueiter, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Large margin semi-tied covariance transforms for discriminative training

George Saon, Hagen Soltau, Daniel Povey, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Frame discrimination training for HMMs for large vocabulary speech recognition

Daniel Povey, Philip C. Woodland, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

A basis representation of constrained MLLR transforms for robust adaptation

Kaisheng Yao, Daniel Povey, 2012, Comput. Speech Lang..

A novel estimation of feature-space MLLR for full-covariance models

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Parallel training of DNNs with Natural Gradient and Parameter Averaging

Sanjeev Khudanpur, Daniel Povey, Xiaohui Zhang, 2014 .

Strategies for training large scale neural network language models

Lukás Burget, Jan Cernocký, Daniel Povey, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Corrections to "Automatic Transcription of Conversational Telephone Speech"

Mark J. F. Gales, Lan Wang, Daniel Povey, 2006, IEEE Trans. Speech Audio Process..

Approaches to automatic lexicon learning with limited training examples

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Advances in speech transcription at IBM under the DARPA EARS program

Geoffrey Zweig, Brian Kingsbury, George Saon, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

Acoustic Modelling from the Signal Domain Using CNNs

Sanjeev Khudanpur, Daniel Povey, Pegah Ghahremani, 2016, INTERSPEECH.

End-to-end Deep Neural Network Age Estimation

Sanjeev Khudanpur, Daniel Povey, Nanxin Chen, 2018, INTERSPEECH.

New features in the CU-HTK system for transcription of conversational telephone speech

Daniel Povey, Thomas Hain, Gunnar Evermann, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Large scale discriminative training for speech recognition

Daniel Povey, Philip C. Woodland, P. Woodland, 2000 .

MUSAN: A Music, Speech, and Noise Corpus pdf

Daniel Povey, David Snyder, Guoguo Chen, 2015, ArXiv.

MMI-MAP and MPE-MAP for acoustic model adaptation

Mark J. F. Gales, Daniel Povey, Philip C. Woodland, 2003, INTERSPEECH.

Emotion Identification from Raw Speech Signals Using DNNs

Kandarpa Kumar Sarma, Daniel Povey, Najim Dehak, 2018, INTERSPEECH.

Advances in Arabic Speech Transcription at IBM Under the DARPA GALE Program

Brian Kingsbury, George Saon, Hagen Soltau, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

Improving LF-MMI Using Unconstrained Supervisions for ASR

Sanjeev Khudanpur, Daniel Povey, Hossein Sameti, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Acoustic data-driven pronunciation lexicon generation for logographic languages

Sanjeev Khudanpur, Daniel Povey, Guoguo Chen, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Generating exact lattices in the WFST framework

Ngoc Thang Vu, Petr Motlícek, Lukás Burget, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Low Latency Acoustic Modeling Using Temporal Convolution and LSTMs

Yiming Wang, Sanjeev Khudanpur, Daniel Povey, 2018, IEEE Signal Processing Letters.

Penalty function maximization for large margin HMM training

George Saon, Daniel Povey, 2008, INTERSPEECH.

Minimum hypothesis phone error as a decoding method for speech recognition

Haihua Xu, Jie Zhu, Daniel Povey, 2009, INTERSPEECH.

Acoustic Data-Driven Lexicon Learning Based on a Greedy Pronunciation Selection Framework

Xiaohui Zhang, Sanjeev Khudanpur, Daniel Povey, 2017, INTERSPEECH.

JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS

Sanjeev Khudanpur, Daniel Povey, Tom Ko, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

The Impact of ASR on Speech-to-Speech Translation Performance

Bowen Zhou, Ruhi Sarikaya, Yuqing Gao, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Improved feature processing for deep neural networks

Jan Cernocký, Daniel Povey, Karel Veselý, 2013, INTERSPEECH.

Automatic transcription of conversational telephone speech

Mark J. F. Gales, Lan Wang, Daniel Povey, 2005, IEEE Transactions on Speech and Audio Processing.

Phone Duration Modeling for LVCSR Using Neural Networks

Sanjeev Khudanpur, Daniel Povey, Hossein Sameti, 2017, INTERSPEECH.

Reverberation robust acoustic modeling using i-vectors with time delay neural networks

Sanjeev Khudanpur, Daniel Povey, Vijayaditya Peddinti, 2015, INTERSPEECH.

A diversity-penalizing ensemble training method for deep learning

Xiaohui Zhang, Sanjeev Khudanpur, Daniel Povey, 2015, INTERSPEECH.

Some insights from translating conversational telephone speech

Matt Post, Sanjeev Khudanpur, Daniel Povey, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Subspace Gaussian Mixture Models for speech recognition

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Discriminative training for HMM-based offline handwritten character recognition

Daniel Povey, Roongroj Nopsuwanchai, Daniel Povey, 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

Anatomy of an extremely fast LVCSR decoder

Geoffrey Zweig, George Saon, Daniel Povey, 2005, INTERSPEECH.

Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition

Yiming Wang, Ke Li, Sanjeev Khudanpur, 2018, INTERSPEECH.

Phone duration modeling for LVCSR

Daniel Povey, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Flat-Start Single-Stage Discriminatively Trained HMM-Based Models for ASR

Sanjeev Khudanpur, Daniel Povey, Hossein Sameti, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

A pitch extraction algorithm tuned for automatic speech recognition

Sanjeev Khudanpur, Daniel Povey, Bagher BabaAli, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The subspace Gaussian mixture model - A structured model for speech recognition

Kai Feng, Ariya Rastrow, Lukás Burget, 2011, Comput. Speech Lang..

Speaking rate adaptation using continuous frame rate normalization

Daniel Povey, Stephen M. Chu, Daniel Povey, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

End-to-end Speech Recognition Using Lattice-free MMI

Sanjeev Khudanpur, Daniel Povey, Hossein Sameti, 2018, INTERSPEECH.

Combination of FST and CN search in spoken term detection

Alexander I. Rudnicky, Daniel Povey, Yun Wang, 2014, INTERSPEECH.

Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification

Daniel Povey, David Snyder, Brian Kan-Wing Mak, 2018, INTERSPEECH.

A time delay neural network architecture for efficient modeling of long temporal contexts

Sanjeev Khudanpur, Daniel Povey, Vijayaditya Peddinti, 2015, INTERSPEECH.

Strategies for using MLP based features with limited target-language training data

Jia Liu, Daniel Povey, Ji Xu, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks

Yiming Wang, Ke Li, Sanjeev Khudanpur, 2018, INTERSPEECH.

A Time-Restricted Self-Attention Layer for ASR

Ke Li, Sanjeev Khudanpur, Daniel Povey, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Librispeech: An ASR corpus based on public domain audio books

Sanjeev Khudanpur, Daniel Povey, Guoguo Chen, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Investigation of transfer learning for ASR using LF-MMI trained neural networks

Sanjeev Khudanpur, Daniel Povey, Pegah Ghahremani, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Far-Field ASR Without Parallel Data

Yiming Wang, Sanjeev Khudanpur, Daniel Povey, 2016, INTERSPEECH.

Large scale discriminative training of hidden Markov models for speech recognition

Daniel Povey, Philip C. Woodland, P. Woodland, 2002, Comput. Speech Lang..

Evaluation of Proposed Modifications to MPE for Large Scale Discriminative Training

Brian Kingsbury, Daniel Povey, Brian Kingsbury, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

DIARIZATION USING DEEP NEURAL NETWORK EMBEDDINGS

Daniel Povey, Alan McCree, Daniel Garcia-Romero, 2017 .

fMPE: discriminatively trained features for speech recognition

Geoffrey Zweig, Brian Kingsbury, George Saon, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Quick fmllr for speaker adaptation in speech recognition

Daniel Povey, Balakrishnan Varadarajan, Selina M. Chu, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

The 2009 IBM GALE Mandarin broadcast transcription system

Yong Qin, Daniel Povey, Qin Shi, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Automated Quality Monitoring in the Call Center with ASR and Maximum Entropy

Geoffrey Zweig, Brian Kingsbury, Bhuvana Ramabhadran, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Audio augmentation for speech recognition

Sanjeev Khudanpur, Daniel Povey, Tom Ko, 2015, INTERSPEECH.

Boosted MMI for model and feature-space discriminative training

Brian Kingsbury, Bhuvana Ramabhadran, George Saon, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improvements to fMPE for discriminative training of features

Daniel Povey, Daniel Povey, 2005, INTERSPEECH.

A study on data augmentation of reverberant speech for robust speech recognition

Sanjeev Khudanpur, Daniel Povey, Tom Ko, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Monte Carlo model-space noise adaptation for speech recognition

Brian Kingsbury, Daniel Povey, 2008, INTERSPEECH.

The IBM 2006 Gale Arabic ASR System

Geoffrey Zweig, Brian Kingsbury, George Saon, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

The IBM Rich Transcription Spring 2006 Speech-to-Text System for Lecture Meetings

Jing Huang, Olivier Siohan, Daniel Povey, 2006, MLMI.

Neural Network Language Modeling with Letter-Based Features and Importance Sampling

Jian Wang, Yiming Wang, Ke Li, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Modeling gender dependency in the Subspace GMM framework

Ngoc Thang Vu, Tanja Schultz, Daniel Povey, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The IBM 2004 conversational telephony system for rich transcription

Geoffrey Zweig, Brian Kingsbury, George Saon, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

State-Level Data Borrowing for Low-Resource Speech Recognition Based on Subspace GMMs

Jia Liu, Daniel Povey, Yanmin Qian, 2011, INTERSPEECH.

Automatic transcription of conversational telephone speech: development of the CU-HTK 2002 system

Daniel Povey, Thomas Hain, Xunying Liu, 2003 .

Sequence-discriminative training of deep neural networks

Lukás Burget, Daniel Povey, Karel Veselý, 2013, INTERSPEECH.

A GPU-based WFST Decoder with Exact Lattice Generation pdf

Justin Luitjens, Yiming Wang, Sanjeev Khudanpur, 2018, INTERSPEECH.

Secondary Classification for GMM Based Speaker Recognition

Daniel Povey, Jason W. Pelecanos, Ganesh N. Ramaswamy, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

The Kaldi OpenKWS System: Improving Low Resource Keyword Search

Xiaohui Zhang, Yiming Wang, Sanjeev Khudanpur, 2017, INTERSPEECH.

A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition

Yiming Wang, Ke Li, Sanjeev Khudanpur, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Large scale MMIE training for conversational telephone speech recognition

Daniel Povey, Philip C. Woodland, 2000 .

Pronunciation and silence probability modeling for ASR

Sanjeev Khudanpur, Daniel Povey, Minhua Wu, 2015, INTERSPEECH.

Universal background model based speech recognition

Daniel Povey, Balakrishnan Varadarajan, Selina M. Chu, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improved discriminative training techniques for large vocabulary continuous speech recognition

Daniel Povey, Philip C. Woodland, P. Woodland, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Revisiting Recurrent Neural Networks for robust ASR

Daniel Povey, Oriol Vinyals, Suman V. Ravuri, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Minimum Phone Error and I-smoothing for improved discriminative training

Daniel Povey, Philip C. Woodland, P. Woodland, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Fast speaker adaptive training for speech recognition

Hagen Soltau, Daniel Povey, Hong-Kwang Jeff Kuo, 2008, INTERSPEECH.

A keyword search system using open source software

David Yarowsky, Xiaohui Zhang, Florian Metze, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

Parallel training of Deep Neural Networks with Natural Gradient and Parameter Averaging pdf

Xiaohui Zhang, Sanjeev Khudanpur, Daniel Povey, 2014, ICLR.

Acoustic Modeling from Frequency Domain Representations of Speech

Sanjeev Khudanpur, Daniel Povey, Hang Lv, 2018, INTERSPEECH.

Backstitch: Counteracting Finite-Sample Bias via Negative Steps

Xiaohui Zhang, Yiming Wang, Sanjeev Khudanpur, 2017, INTERSPEECH.

Revisiting semi-continuous hidden Markov models

Daniel Povey, Tobias Bocklet, Korbinian Riedhammer, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Semi-supervised maximum mutual information training of deep neural network acoustic models

Sanjeev Khudanpur, Daniel Povey, Vimal Manohar, 2015, INTERSPEECH.

A Teacher-Student Learning Approach for Unsupervised Domain Adaptation of Sequence-Trained ASR Models

Sanjeev Khudanpur, Daniel Povey, Pegah Ghahremani, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Quantifying the value of pronunciation lexicons for keyword search in lowresource languages

David Yarowsky, Sanjeev Khudanpur, Daniel Povey, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models

Kai Feng, Ariya Rastrow, Lukás Burget, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

A basis method for robust estimation of constrained MLLR

Kaisheng Yao, Daniel Povey, Daniel Povey, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Feature and model space speaker adaptation with full covariance Gaussians

George Saon, Daniel Povey, 2006, INTERSPEECH.

Porting: SwitchBoard to the VoiceMail task

Mark J. F. Gales, Yuan Dong, Daniel Povey, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Modeling phonetic context with non-random forests for speech recognition

Sanjeev Khudanpur, Daniel Povey, Hainan Xu, 2015, INTERSPEECH.

Using ASR Methods for OCR

Shinji Watanabe, Sanjeev Khudanpur, Daniel Povey, 2019, 2019 International Conference on Document Analysis and Recognition (ICDAR).

An Exploration of Dropout with LSTMs

Yonghong Yan, Sanjeev Khudanpur, Daniel Povey, 2017, INTERSPEECH.

A symmetrization of the Subspace Gaussian Mixture Model

Daniel Povey, Martin Karafiát, Arnab Ghoshal, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Coarse-Grained Model for Optimal Coupling of ASR and SMT Systems for Speech Translation

Sanjeev Khudanpur, Daniel Povey, Gaurav Kumar, 2015, EMNLP.

Removing redundancy from lattices

Hagen Soltau, Hermann Ney, Daniel Povey, 2014, INTERSPEECH.

Discriminative map for acoustic model adaptation

Mark J. F. Gales, Daniel Povey, Philip C. Woodland, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

JHU Kaldi system for Arabic MGB-3 ASR challenge using diarization, audio-transcript alignment and transfer learning

Sanjeev Khudanpur, Daniel Povey, Vimal Manohar, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

XMLLR for improved speaker adaptation in speech recognition

Daniel Povey, Hong-Kwang Jeff Kuo, 2008, INTERSPEECH.

The IBM 2008 GALE Arabic speech transcription system

Brian Kingsbury, George Saon, Hagen Soltau, 2010, ICASSP.

Krylov Subspace Descent for Deep Learning

Daniel Povey, Oriol Vinyals, Oriol Vinyals, 2011, AISTATS.

Feature and score level combination of subspace Gaussinas in LVCSR task

Petr Motlícek, Daniel Povey, Martin Karafiát, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Combining forward and backward search in decoding

Geoffrey Zweig, Daniel Povey, Mirko Hannemann, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improving deep neural network acoustic models using generalized maxout networks

Xiaohui Zhang, Sanjeev Khudanpur, Daniel Povey, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An improved consensus-like method for Minimum Bayes Risk decoding and lattice combination

Haihua Xu, Jie Zhu, Daniel Povey, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Feature space Gaussianization

George Saon, Daniel Povey, Satya Dharanipragada, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Using proxies for OOV keywords in the keyword search task

Sanjeev Khudanpur, Daniel Povey, Oguz Yilmaz, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Output-Gate Projected Gated Recurrent Unit for Speech Recognition

Yonghong Yan, Lu Huang, Sanjeev Khudanpur, 2018, INTERSPEECH.

Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI

Yiming Wang, Sanjeev Khudanpur, Daniel Povey, 2016, INTERSPEECH.

Automated Quality Monitoring for Call Centers using Speech and NLP Technologies

Geoffrey Zweig, Brian Kingsbury, Bhuvana Ramabhadran, 2006, NAACL.

Semi-Supervised Training of Acoustic Models Using Lattice-Free MMI

Sanjeev Khudanpur, Daniel Povey, Vimal Manohar, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Tutorial-style Introduction to Subspace Gaussian Mixture Models for Speech Recognition

Daniel Povey, Daniel Povey, 2009 .

Discriminatively trained features using fMPE for multi-stream audio-visual speech recognition

Jing Huang, Daniel Povey, 2005, INTERSPEECH.

Multilingual deep neural network based acoustic modeling for rapid language adaptation

Ngoc Thang Vu, Tanja Schultz, Petr Motlícek, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The Kaldi Speech Recognition Toolkit

Daniel Povey, Mirko Hannemann, Georg Stemmer, 2011 .

SPAM and full covariance for speech recognition

Daniel Povey, 2006, INTERSPEECH.

LET-Decoder: A WFST-Based Lazy-Evaluation Token-Group Decoder With Exact Lattice Generation

Lei Xie, Sanjeev Khudanpur, Daniel Povey, 2021, IEEE Signal Processing Letters.

A Parallelizable Lattice Rescoring Strategy with Neural Language Models

Sanjeev Khudanpur, Daniel Povey, Ke Li, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Lhotse: a speech data representation library for the modern deep learning ecosystem pdf

Sanjeev Khudanpur, Daniel Povey, Piotr Zelasko, 2021, ArXiv.

speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment pdf

Daniel Povey, Yujun Wang, Ke Li, 2021, Interspeech.

An Asynchronous WFST-Based Decoder for Automatic Speech Recognition

Lei Xie, Sanjeev Khudanpur, Daniel Povey, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Wake Word Detection with Streaming Transformers

Lei Xie, Sanjeev Khudanpur, Daniel Povey, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10, 000 Hours of Transcribed Audio pdf

Xiangang Li, Shinji Watanabe, Xuchen Yao, 2021, Interspeech.

Low Development Cost , High Quality Speech Recognition for New Languages and Domains ” : Report from 2009 Johns Hopkins / CLSP Summer Workshop

Ariya Rastrow, Daniel Povey, Martin Karafiát, 2009 .

PAID I FEATURE AND SCORE LEVEL COMBINATION OF SUBSPACE GAUSSIANS IN LVCSR TASK

Daniel Povey, Martin Karafiat, Petr Motlicek, 2013 .

Feature and model space speaker adaptati

Daniel Povey, 2006 .

The Symmetric Subspace Gaussian Mixture Model

Daniel Povey, Way, Redmond, 2010 .