Jeff Z. Ma

According to our database1, Jeff Z. Ma authored at least 30 papers between 1999 and 2018.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Other 

Links

On csauthors.net:

Bibliography

2018
Optimizing Multilingual Knowledge Transfer for Time-Delay Neural Networks with Low-Rank Factorization.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
Improving Deliverable Speech-to-Text Systems with Multilingual Knowledge Transfer.
Proceedings of the Interspeech 2017, 2017

Improved Single System Conversational Telephone Speech Recognition with VGG Bottleneck Features.
Proceedings of the Interspeech 2017, 2017

2015
Large-scale speaker search using PLDA on mismatched conditions.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Robust speech recognition in unknown reverberant and noisy conditions.
Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2014
Neural Network Bottleneck Features for Language Identification.
Proceedings of the Odyssey 2014: The Speaker and Language Recognition Workshop, 2014

Domain adaptation via within-class covariance correction in I-vector based speaker recognition systems.
Proceedings of the IEEE International Conference on Acoustics, 2014

2013
Improvements in language identification on the RATS noisy speech corpus.
Proceedings of the INTERSPEECH 2013, 2013

Developing a speaker identification system for the DARPA RATS project.
Proceedings of the IEEE International Conference on Acoustics, 2013

2012
Patrol Team Language Identification System for DARPA RATS P1 Evaluation.
Proceedings of the INTERSPEECH 2012, 2012

2011
BBN's Systems for the Chinese-English Sub-task of the NTCIR-9 PatentMT Evaluation.
Proceedings of the 9th NTCIR Workshop Meeting on Evaluation of Information Access Technologies: Information Retrieval, 2011

2009
Unsupervised acoustic and language model training with small amounts of labelled data.
Proceedings of the IEEE International Conference on Acoustics, 2009

2008
Unsupervised versus supervised training of acoustic models.
Proceedings of the INTERSPEECH 2008, 2008

2007
Unsupervised Training on a Large Amount of Arabic Broadcast News Data.
Proceedings of the IEEE International Conference on Acoustics, 2007

2006
Advances in transcription of broadcast news and conversational telephone speech within the combined EARS BBN/LIMSI system.
IEEE Trans. Audio, Speech & Language Processing, 2006

Unsupervised Training on Large Amounts of Broadcast News Data.
Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005
The 2004 BBN/LIMSI 20xRT English conversational telephone speech recognition system.
Proceedings of the INTERSPEECH 2005, 2005

Improvements to the BBN RT04 Mandarin conversational telephone speech recognition system.
Proceedings of the INTERSPEECH 2005, 2005

2004
Target-directed mixture dynamic models for spontaneous speech recognition.
IEEE Trans. Speech and Audio Processing, 2004

A mixed-level switching dynamic system for continuous speech recognition.
Computer Speech & Language, 2004

Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system.
Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003
Efficient decoding strategies for conversational speech recognition using a constrained nonlinear state-space model.
IEEE Trans. Speech and Audio Processing, 2003

2002
Training topic classifiers for conversational speech with limited data.
Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Investigation of speech recognition over IP channels.
Proceedings of the IEEE International Conference on Acoustics, 2002

A mixture linear model with target-directed dynamics for spontaneous speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2002

2001
Parameter estimation of a target-directed dynamic system model with switching states.
Signal Processing, 2001

Efficient decoding strategy for conversational speech recognition using state-space models for vocal-tract-resonance dynamics.
Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

2000
A path-stack algorithm for optimizing dynamic regimes in a statistical hidden dynamic model of speech.
Computer Speech & Language, 2000

1999
Optimization of dynamic regimes in a statistical hidden dynamic model for conversational speech recognition.
Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

A statistical coarticulatory model for the hidden vocal-tract-resonance dynamics.
Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999


  Loading...