Spyros Matsoukas
Cited by
Cited by
Combining outputs from multiple machine translation systems
AVI Rosti, NF Ayan, B Xiang, S Matsoukas, R Schwartz, B Dorr
Human Language Technologies 2007: The Conference of the North American …, 2007
Combining outputs from multiple machine translation systems
BD Antti-Veikko I Rosti, Necip Fazil Ayan, Bing Xiang, Spyros Matsoukas ...
Human Language Technologies 2007: The Conference of the North American …, 2007
Machine translation of Arabic dialects
R Zbib, E Malchiodi, J Devlin, D Stallard, S Matsoukas, R Schwartz, ...
Proceedings of the 2012 conference of the north american chapter of the …, 2012
Improved word-level system combination for machine translation
AVI Rosti, S Matsoukas, R Schwartz
45th Annual Meeting of the Association of Computational Linguistics 45 (1 …, 2007
Multi-task learning and weighted cross-entropy for DNN-based keyword spotting.
S Panchapagesan, M Sun, A Khare, S Matsoukas, A Mandal, ...
Interspeech 9, 760-764, 2016
Keyword detection modeling using contextual and environmental information
R Prasad, KJ Basye, S Matsoukas, R Ramachandran, SNP Vitaladevuni, ...
US Patent 9,697,828, 2017
Discriminative corpus weight estimation for machine translation
S Matsoukas, AV Rosti, B Zhang
Proceedings of the 2009 conference on empirical methods in natural language …, 2009
Developing a speech activity detection system for the DARPA RATS program
T Ng, B Zhang, L Nguyen, S Matsoukas, X Zhou, N Mesgarani, K Veselý, ...
Thirteenth annual conference of the international speech communication …, 2012
Determining speaker direction using a spherical microphone array
JW McDonough Jr, VS Leutnant, SVSSR Krishna, S Matsoukas
US Patent 9,560,441, 2017
Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting
M Sun, A Raju, G Tucker, S Panchapagesan, G Fu, A Mandal, ...
2016 IEEE Spoken Language Technology Workshop (SLT), 474-480, 2016
Compressed Time Delay Neural Network for Small-Footprint Keyword Spotting.
M Sun, D Snyder, Y Gao, VK Nagaraja, M Rodehorst, S Panchapagesan, ...
Interspeech, 3607-3611, 2017
Practical implementations of speaker-adaptive training
S Matsoukas, R Schwartz, H Jin, L Nguyen
DARPA speech recognition workshop, 1997
Advances in transcription of broadcast news and conversational telephone speech within the combined EARS BBN/LIMSI system
S Matsoukas, JL Gauvain, G Adda, T Colthurst, CL Kao, O Kimball, ...
IEEE Transactions on Audio, Speech, and Language Processing 14 (5), 1541-1556, 2006
Unsupervised training on large amounts of broadcast news data
J Ma, S Matsoukas, O Kimball, R Schwartz
2006 IEEE International Conference on Acoustics Speech and Signal Processing …, 2006
Domain adaptation via within-class covariance correction in i-vector based speaker recognition systems
O Glembek, J Ma, P Matějka, B Zhang, O Plchot, L Bürget, S Matsoukas
2014 IEEE international conference on acoustics, speech and signal …, 2014
Incremental hypothesis alignment for building confusion networks with application to machine translation system combination
AV Rosti, B Zhang, S Matsoukas, R Schwartz
Proceedings of the Third Workshop on Statistical Machine Translation, 183-186, 2008
Discriminatively trained region dependent feature transforms for speech recognition
B Zhang, S Matsoukas, R Schwartz
2006 IEEE International Conference on Acoustics Speech and Signal Processing …, 2006
The 1996 BBN byblos HUB-4 transcription system
F Kubala, H Jin, S Matsoukas, L Nguyen, R Schwartz, J Makhoul
Proceedings of the 1997 DARPA Speech Recognition Workshop, 90-93, 1997
Robust i-vector based adaptation of DNN acoustic model for speech recognition
S Garimella, A Mandal, N Strom, B Hoffmeister, S Matsoukas, ...
Sixteenth Annual Conference of the International Speech Communication …, 2015
Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system
R Schwartz, T Colthurst, N Duta, H Gish, R Iyer, CL Kao, D Liu, O Kimball, ...
2004 IEEE International Conference on Acoustics, Speech, and Signal …, 2004
The system can't perform the operation now. Try again later.
Articles 1–20