Xiaodong Cui  Xiaodong Cui photo       

contact information

Research Staff Member
Thomas J. Watson Research Center, Yorktown Heights, NY USA
  +1dash914dash945dash3863

links

Professional Associations

Professional Associations:  IEEE Signal Processing Society   |  IEEE, Senior Member


2017

Embedding-based speaker adaptive training of deep neural networks
Xiaodong Cui, Vaibhava Goel and George Saon
Interspeech, 2017

English conversational telephone speech recognition by humans and machines
George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi and Phil Hall
Interspeech, 2017


2016

Maximum likelihood nonlinear transformations based on deep neural networks
Xiaodong Cui and Vaibhava Goel
IEEE/ACM Transactions on Audio, Speech, and Language Processing 24(11), 2023--2031, 2016

Efficient non-linear feature adaptation using maxout networks
Steven Rennie, Xiaodong Cui and Vaibhava Goel
Acoustics, Speech and Signal Processing (ICASSP), IEEE International Conference on , pp. 5310--5314, 2016


2015

Data augmentation for deep neural network acoustic modeling
Xiaodong Cui, Vaibhava Goel, Brian Kingsbury
IEEE/ACM Transactions on Audio, Speech and Language Processing 23(9), 1469-1477, 2015

Maximum likelihood nonlinear transformations based on deep neural networks
Xiaodong Cui, Vaibhava Goel
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 4320--4324

Annealed dropout trained maxout networks for improved LVCSR
Steven J Rennie, Pierre L Dognin, Xiaodong Cui, Vaibhava Goel
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 5181--5185

Data augmentation for deep convolutional neural network acoustic modeling
Xiaodong Cui, Vaibhava Goel, Brian Kingsbury
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 4545--4549


2014

A family of discriminative training criteria based on the F-divergence for deep neural networks
Markus Nussbaum-Thom, Xiaodong Cui, Ralf Schluter, Vaibhava Goel, Hermann Ney
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pp. 5612--5616

Exploiting vocal-source features to improve ASR accuracy for low-resource languages
Raul Fernandez, Jia Cui, Andrew Rosenberg, Bhuvana Ramabhadran, Xiaodong Cui
INTERSPEECH, 2014

Improving deep neural network acoustic modeling for audio corpus indexing under the IARPA Babel program
Xiaodong Cui, Brian Kingsbury, Jia Cui, Bhuvana Ramabhadran, Andrew Rosenberg, Mohammad Sadegh Rasooli, Owen Rambow, Nizar Habash, Vaibhava Goel
INTERSPEECH, 2014

Data augmentation for deep neural network acoustic modeling
Xiaodong Cui, Vaibhava Goel, Brian Kingsbury
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pp. 5582--5586


2013

Developing keyword search under the IARPA Babel program
Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark JF Gales, Brian Kingsbury, Kate Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, others
Afeka Speech Processing Conference, 2013

Adaptive stereo-based stochastic mapping.
Shay Maymon, Pierre L Dognin, Xiaodong Cui, Vaibhava Goel
INTERSPEECH, pp. 3517--3521, 2013

Mixtures of Bayesian joint factor analyzers for noise robust automatic speech recognition.
Xiaodong Cui, Vaibhava Goel, Brian Kingsbury
INTERSPEECH, pp. 3012--3016, 2013

Stereo hidden Markov modeling for noise robust speech recognition
Xiaodong Cui, Mohamed Afify, Yuqing Gao, Bowen Zhou
Computer Speech and Language 27(2), 407--419, Elsevier, 2013

System combination and score normalization for spoken term detection
Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark JF Gales, Brian Kingsbury, Kate Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, others
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, 8272--8276

An empirical study of confusion modeling in keyword search for low resource languages
Murat Saraclar, Abhinav Sethy, Bhuvana Ramabhadran, Lidia Mangu, Jia Cui, Xiaodong Cui, Brian Kingsbury, Jonathan Mamou
Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on, pp. 464--469

Developing speech recognition systems for corpus indexing under the IARPA Babel program
Jia Cui, Xiaodong Cui, J Mamou, B Kingsbury, B Ramabhadran, L Mangu, M Picheny, A Sethy, J Kim
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp. 6753--6757

A high-performance Cantonese keyword search system
Brian Kingsbury, Jia Cui, Xiaodong Cui, Mark JF Gales, Kate Knill, Jonathan Mamou, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, others
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pp. 8277--8281

The IBM speech-to-speech translation system for smartphone: improvements for resource-constrained tasks
Bowen Zhou, Xiaodong Cui, Songfang Huang, Martin Cmejrek, Wei Zhang, Jian Xue, Jia Cui, Bing Xiang, Gregg Daggett, Upendra V. Chaudhari, Sameer Maskey, Etienne Marcheret
Computer Speech and Language 27(2), 592-618, Elsevier, 2013


2012

Sparse Bayesian Factor Analysis for Stereo-based Stochastic Mapping.
Xiaodong Cui, Mohamed Afify, George Saon, Vaibhava Goel
INTERSPEECH, 2012

Stereo-based stochastic mapping with context using probabilistic PCA for noise robust automatic speech recognition
Xiaodong Cui, Mohamed Afify, Bowen Zhou
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on, pp. 4705--4708

Multi-view and multi-objective semi-supervised learning for HMM-based automatic speech recognition
Xiaodong Cui, Jing Huang, Jen-Tzung Chien
Audio, Speech, and Language Processing, IEEE Transactions on 20(7), 1923--1935, IEEE, 2012

Hidden Markov acoustic modeling with bootstrap and restructuring for low-resourced languages
Xiaodong Cui, Jian Xue, Xin Chen, Peder A Olsen, Pierre L Dognin, Upendra V Chaudhari, John R Hershey, Bowen Zhou
Audio, Speech, and Language Processing, IEEE Transactions on 20(8), 2252--2264, IEEE, 2012


2011

An investigation of heuristic, manual and statistical pronunciation derivation for Pashto
Upendra V Chaudhari, Xiaodong Cui, Bowen Zhou, Rong Zhang
Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE Workshop on, pp. 249--253

Clustering of bootstrapped acoustic model with full covariance
Xin Chen, Xiaodong Cui, Jian Xue, Peder Olsen, John Hershey, Bowen Zhou, Yunxin Zhao
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 4496--4499

Towards high performance LVCSR in speech-to-speech translation system on smart phones
Jian Xue, Xiaodong Cui, Gregg Daggett, Etienne Marcheret, Bowen Zhou
INTERSPEECH, pp. 2861--2864, 2011

Acoustic modeling with bootstrap and restructuring based on full covariance
Xiaodong Cui, Xin Chen, Jian Xue, Peder A Olsen, John R Hershey, Bowen Zhou
INTERSPEECH, pp. 1697--1700, 2011

Multi-view and multi-objective semi-supervised learning for large vocabulary continuous speech recognition
Xiaodong Cui, Jing Huang, Jen-Tzung Chien
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pp. 4668--4671


2010


Cross-view transfer learning for automatic speech recognition
Jing Huang, Xiaodong Cui, Jen-Tzung Chien
NIPS 2010 Workshop on Transfer Learning by Learning Rich Generative Models

A comparative study on system combination schemes for LVCSR
Chengyuan Ma, Hong-Kwang Jeff Kuo, Hagen Soltau, Xiaodong Cui, Upendra Chaudhari, Lidia Mangu, Chin-Hui Lee
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on, pp. 4394--4397

Acoustic modeling with bootstrap and restructuring for low-resourced languages.
Xiaodong Cui, Jian Xue, Pierre L Dognin, Upendra V Chaudhari, Bowen Zhou
INTERSPEECH, pp. 2974--2977, 2010


2009

Stereo-based stochastic mapping for robust speech recognition
Mohamed Afify, Xiaodong Cui, Yuqing Gao
Audio, Speech, and Language Processing, IEEE Transactions on 17(7), 1325--1334, IEEE, 2009

Stereo-based stochastic mapping with discriminative training for noise robust speech recognition
Xiaodong Cui, Mohamed Afify, Yuqing Gao
Acoustics Speech and Signal Processing (ICASSP), 2009 IEEE International Conference on, pp. 3933--3936

Improving Online Incremental Speaker Adaptation with Eigen Feature Space MLLR
Xiaodong Cui, Jian Xue, Bowen Zhou
Automatic Speech Recognition and Understanding (ASRU), 2009 IEEE Workshop on, pp. 136--140



2008

N-best based stochastic mapping on stereo HMM for noise robust speech recognition.
Xiaodong Cui, Mohamed Afify, Yuqing Gao
INTERSPEECH, pp. 1261--1264, 2008


MMSE-based stereo feature stochastic mapping for noise robust speech recognition
Xiaodong Cui, Mohamed Afify, Yuqing Gao
Acoustics Speech and Signal Processing (ICASSP), 2008 IEEE International Conference on, pp. 4077--4080

Developing high performance ASR in the IBM multilingual speech-to-speech translation system
Xiaodong Cui, Liang Gu, Bing Xiang, Wei Zhang, Yuqing Gao
Acoustics Speech and Signal Processing (ICASSP), 2008 IEEE International Conference on, pp. 5121--5124


2007

Robust speaker adaptation by weighted model averaging based on the minimum description length criterion
Xiaodong Cui, Abeer Alwan
Audio, Speech, and Language Processing, IEEE Transactions on 15(2), 652--660, IEEE, 2007

Speaker adaptation with limited data using regression-tree-based spectral peak alignment
Shizhen Wang, Xiaodong Cui, Abeer Alwan
Audio, Speech, and Language Processing, IEEE Transactions on 15(8), 2454--2464, IEEE, 2007

A study of variable-parameter Gaussian mixture hidden Markov modeling for noisy speech recognition
Xiaodong Cui, Yifan Gong
Audio, Speech, and Language Processing, IEEE Transactions on 15(4), 1366--1376, IEEE, 2007


2006

Modeling variance variation in a variable parameter HMM framework for noise robust speech recognition
Xiaodong Cui, Yifan Gong
Acoustics Speech and Signal Processing (ICASSP), 2006 IEEE International Conference on, pp. I--I

A database of vocal tract resonance trajectories for research in speech processing
Li Deng, Xiaodong Cui, Robert Pruvenok, Yanyi Chen, Safiyy Momen, Abeer Alwan
Acoustics Speech and Signal Processing (ICASSP), 2006 IEEE International Conference on, pp. I--I



2005

Noise robust speech recognition using feature compensation based on polynomial regression of utterance SNR
Xiaodong Cui, Abeer Alwan
Speech and Audio Processing, IEEE Transactions on 13(6), 1161--1172, IEEE, 2005

MLLR-like speaker adaptation based on linearization of VTLN with MFCC features
Xiaodong Cui, Abeer Alwan
INTERSPEECH, 2005

TBALL data collection: the making of a young children's speech corpus.
Abe Kazemzadeh, Hong You, Markus Iseli, Barbara Jones, Xiaodong Cui, Margaret Heritage, Patti Price, Elaine Andersen, Shrikanth Narayanan, Abeer Alwan
INTERSPEECH, pp. 1581--1584, 2005


2004

Combining feature compensation and weighted Viterbi decoding for noise robust speech recognition with limited adaptation data
Xiaodong Cui, Abeer Alwan
Acoustics Speech and Signal Processing (ICASSP), 2004 IEEE International Conference on, pp. I--969

Can back-ends be more robust than front-ends? Investigation over the Aurora-2 database
Alexis Bernard, Yifan Gong, Xiaodong Cui
Acoustics Speech and Signal Processing (ICASSP), 2004 IEEE International Conference on, pp. I--1025


2003


Variable parameter Gaussian mixture hidden Markov modeling for speech recognition
Xiaodong Cui, Yifan Gong
Acoustics Speech and Signal Processing (ICASSP), 2003 IEEE International Conference on, pp. I--12


2002

Evaluation of noise robust features on the Aurora databases.
Xiaodong Cui, Markus Iseli, Qifeng Zhu, Abeer Alwan
INTERSPEECH, 2002

Efficient adaptation text design based on the Kullback-Leibler measure
Xiaodong Cui, Abeer Alwan
Acoustics, Speech, and Signal Processing (ICASSP), 2002 IEEE International Conference on, pp. I--613


2001

Noise robust feature extraction for ASR using the Aurora 2 database.
Qifeng Zhu, Markus Iseli, Xiaodong Cui, Abeer Alwan
INTERSPEECH, pp. 185--188, 2001