Patrick Nguyen

Patrick Nguyen's Home Page

Google scholar page: http://scholar.google.com/citations?user=38fqeIYAAAAJ&hl=en

Final presentation from the JHU CLSP workshop 2010 on Speech Recognition:

SCARF-ws2010-Final-Presentation.pdf

Tutorial on SCARF at the JHU Summer School 2010: video, slides (part1, part2), solutions

Invited talk at CMU (courtesy MModal): slides

Check out the SCARF project page:

http://research.microsoft.com/en-us/projects/scarf/

Publications:

Jianfeng Gao, Patrick Nguyen, Xiaolong Li, Chris Thrasher, Mu Li, and Kuansan Wang, A Comparative Study of Bing Web N-gram Language Models for Web Search and Natural Language Processing, in Proceeding of the 33rd Annual ACM SIGIR Conference, Association for Computing Machinery, Inc., 23 July 2010
Geoffrey Zweig, Patrick Nguyen, Jasha Droppo, and Alex Acero, Continuous Speech Recognition with a TF-IDF Acoustic Model, International Speech Communication Association, 2010
Shankar Shivappa, Patrick Nguyen, and Geoffrey Zweig, Discriminative Template Extraction for Direct Modeling, in ICASSP, IEEE, 2010
Geoffrey Zweig and Patrick Nguyen, From Flat Direct Models to Segmental CRF Models, in ICASSP, IEEE, 2010
Geoffrey Zweig and Patrick Nguyen, SCARF: A Segmental Conditional Random Field Toolkit for Speech Recognition, International Speech Communication Association, 2010
Patrick Nguyen and Geoffrey Zweig, Speech Recognition with Flat Direct Models, in IEEE Journal of Selected Topics in Signal Processing, IEEE, 2010
Geoffrey Zweig and Patrick Nguyen, Maximum Mutual Information Multi-phone Units in Direct Modeling, in Interspeech 2009, International Speech Communication Association, September 2009
Geoffrey Zweig and Patrick Nguyen, SCARF: A Segmental CRF Speech Recognition System, no. MSR-TR-2009-54, May 2009
Xiao Li, Patrick Nguyen, Geoffrey Zweig, and Dan Bohus, Leveraging Multiple Query Logs to Improve Language Models for Spoken Query Recognition, in ICASSP, IEEE, April 2009
Daniel Bolanos, Geoffrey Zweig, and Patrick Nguyen, Multi-scale Personalization for Voice Search Applications, in HLT-NAACL 2009, Association for Computational Linguistics, 2009

G. Zweig, P. Nguyen, Y.-C. Ju, Y.-Y. Wang, D. Yu, and A. Acero. The Voice-Rate Dialog System for Consumer Ratings. In Interspeech, 2007.
P. Nguyen, M. Mahajan, and X. He. Training Non-Parametric Features for Statistical Machine Translation. In Second Workshop on Statistical Machine Translation(ACL), 2007.
G. Zweig, Y. C. Ju, P. Nguyen, D. Yu, Y.-Y. Wang, and A. Acero. Voice-Rate: A Dialog System for Consumer Ratings. In HLT, 2007 (demo track).
A. Subramanya, Z. Zhang, A. C. Surendran, P. Nguyen, M. Narasimhan, and A. Acero. A Generative-Discriminative Framework using Ensemble Methods for Text-Dependent Speaker Verification. In ICASSP, 2007.
C. Ma, P. Nguyen, and M. Mahajan. Finding Speaker Identities with a Conditional Maximum Entropy Model. In ICASSP, 2007.
P. Nguyen, and M. Mahajan. Audio/Video Navigation with A/V X-Ray. In SLT, 2006 (demo track).
X. He, A. Menezes, C. Quirk, A. Aue, S. Corston-Oliver, JF. Gao, and P. Nguyen. Microsoft Research Treelet Translation System: NIST MT Evaluation 06. In NIST Machine Translation Workshop, 2006.
P. Nguyen. Panasonic Real-Time Meeting Room STT. In NIST Rich Transcription (Spring), 2004.
Y. Moh, P. Nguyen, and J.-C. Junqua. Towards Domain Independent Speaker Clustering. In ICASSP, 2003.
P. Nguyen, L. Rigazio, and J.-C. Junqua. Large Corpus Experiment for Broadcast News Recognition. In Proceedings of Eurospeech, 2003.
L. Rigazio, P. Nguyen, D. Kryze, and J.-C. Junqua. Large Vocabulary Noise Robustness on Aurora4. In Proceedings of Eurospeech, 2003.
P. Nguyen and J.-C. Junqua. PSTL's Speaker Diarization system. In DARPA/NIST Rich Transcription Workshop, 2003.
P. Nguyen and J.-C. Junqua. PSTL's Speech-to-Text system. In DARPA/NIST Rich Transcription Workshop, 2003.
P. Nguyen SWAMP: An Isometric Frontend for Speaker Clustering. In DARPA/NIST Rich Transcription Workshop, 2003.
P. Nguyen, L. Rigazio, C. Wellekens, and J.-C. Junqua. LU Factorization for Feature Transformation. In ICSLP, 2002.
P. Nguyen, L. Rigazio, J.-C. Junqua, and C. Wellekens. Piecewise Linear Constraints for Model Space Adaptation . In ICASSP, 2002.
Y. Souilmi, L. Rigazio, P. Nguyen, D. Kryze, and J.-C. Junqua. Blind channel estimation based on speech correlation structure. In ICASSP, 2002.
P. Nguyen, L. Rigazio, Y. Moh, and J.-C. Junqua. Rich Transcription 2002: Site Report (PSTL). In NIST Rich Transcription Workshop, 2002.
P. Nguyen, L. Rigazio, C. Wellekens, J.-C. Junqua. Construction of Model-Space Constraints. In ASRU, 2001.
R. Kuhn, F. Perronnin, P. Nguyen, J.-C. Junqua, and L. Rigazio. Very Fast Adaptation with a Compact Context-Dependent Eigenvoice Model. In ICASSP, 2001.
F. Perronnin, R. Kuhn, P. Nguyen, and J.-C. Junqua. Maximum-Likelihood Training of a Bipartite Acoustic Model for Speech Recognition. In ICASSP, 2001.
L. Rigazio, P. Nguyen, D. Kryze, and Jean-C. Junqua. Separating Speaker and Environment Variabilities for Improved Recognition in Non-Stationary Conditions. In Eurospeech, 2001.
P. Nguyen, L. Rigazio, R. Kuhn, J.-C. Junqua, and C. Wellekens. Self-Adaptation Using Eigenvoices for Large-Vocabulary Continuous Speech Recognition. In ITRW on Adaptation (ISCA Workshop), 2001.
R. Kuhn, J.-C. Junqua, P. Nguyen, and N. Niedzielski. Rapid Speaker Adaptation in Eigenvoice Space. In IEEE Transactions on Speech and Audio Processing, VOL. 8, NO. 6, November 2000.
O. Thyes, R. Kuhn, P. Nguyen and J.-C. Junqua. Speaker Identification and Verification using Eigenvoices. In ICSLP, 2000.
P. Nguyen, L. Rigazio, and J.-C. Junqua. EWAVES: An Efficient Decoding Algorithm for Lexical Tree Based Speech Recognition. In ICSLP, 2000.
R. Kuhn, P. Nguyen, J.-C. Junqua, R. Boman, N. Niedzielski, S. Fincke, K. Field, and M. Contolini. Fast Speaker Adaptation using A Priori Knowledge. In ICASSP, 1999.
P. Nguyen, P. Gelin, J.-C. Junqua, and J.-T. Chien. N-Best Based Supervised and Unsupervised Adaptation for Native and Non-Native Speakers in Cars. In ICASSP, 1999.
P. Nguyen, C. Wellekens, and J.-C. Junqua. Maximum likelihood eigenspace and MLLR for speech recognition in noisy environments. In Eurospeech, 1999.
R. Kuhn, P. Nguyen, J.-C. Junqua, L. Goldwasser, N. Niedzielski, S. Fincke, K. Field, and M. Contolini. Eigenvoices for Speaker Adaptation. In ICSLP, 1998.
R. Kuhn, P. Nguyen, J.-C. Junqua, L. Goldwasser, N. Niedzielski, S. Fincke, and K. Field. Eigenfaces and Eigenvoices: Dimensionality Reduction for Specialized Pattern Recognition. In MMSP, 1998.
P. Nguyen. Fast Speaker Adaptation. Master's thesis, 1998.