☰

Samuel Thomas, Ph.D. - Publications

Affiliations: 
Electrical and Computer Engineering Johns Hopkins University, Baltimore, MD 
Area:
automatic speech recognition
Tree Info Grants Similar researchers PubMed Report error

18 high-probability publications. We are testing a new system for linking publications to authors. You can help! If you notice any inaccuracies, please sign in and mark papers as correct or incorrect matches. If you identify any major omissions or other inaccuracies in the publication list, please let us know.

Year Citation  Score
2013 Jansen A, Dupoux E, Goldwater S, Johnson M, Khudanpur S, Church K, Feldman N, Hermansky H, Metze F, Rose R, Seltzer M, Clark P, McGraw I, Varadarajan B, Bennett E, ... ... Thomas S, et al. A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 8111-8115. DOI: 10.1109/ICASSP.2013.6639245  0.525
2013 Jansen A, Thomas S, Hermansky H. Weak top-down constraints for unsupervised acoustic model training Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 8091-8095. DOI: 10.1109/ICASSP.2013.6639241  0.486
2013 Plchot O, Matsoukas S, Matejka P, Dehak N, Ma J, Cumani S, Glembek O, Hermansky H, Mallidi SH, Mesgarani N, Schwartz R, Soufifar M, Tan ZH, Thomas S, Zhang B, et al. Developing a speaker identification system for the DARPA RATS project Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 6768-6772. DOI: 10.1109/ICASSP.2013.6638972  0.598
2013 Thomas S, Seltzer ML, Church K, Hermansky H. Deep neural network features and semi-supervised training for low resource speech recognition Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 6704-6708. DOI: 10.1109/ICASSP.2013.6638959  0.554
2012 Thomas S, Ganapathy S, Hermansky H. Multilingual MLP features for low-resource LVCSR systems Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 4269-4272. DOI: 10.1109/ICASSP.2012.6288862  0.63
2011 Mesgarani N, Thomas S, Hermansky H. Toward optimizing stream fusion in multistream recognition of speech. The Journal of the Acoustical Society of America. 130: EL14-8. PMID 21786862 DOI: 10.1121/1.3595744  0.709
2011 Thomas S, Nguyen P, Zweig G, Hermansky H. MLP based phoneme detectors for automatic speech recognition Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 5024-5027. DOI: 10.1109/ICASSP.2011.5947485  0.601
2011 Povey D, Burget L, Agarwal M, Akyazi P, Kai F, Ghoshal A, Glembek O, Goel N, Karafiát M, Rastrow A, Rose RC, Schwarz P, Thomas S. The subspace Gaussian mixture model - A structured model for speech recognition Computer Speech and Language. 25: 404-439. DOI: 10.1016/J.Csl.2010.06.003  0.343
2010 Ganapathy S, Thomas S, Hermansky H. Temporal envelope compensation for robust phoneme recognition using modulation spectrum. The Journal of the Acoustical Society of America. 128: 3769-80. PMID 21218908 DOI: 10.1121/1.3504658  0.727
2010 Ganapathy S, Thomas S, Hermansky H. Robust spectro-temporal features based on autoregressive models of Hilbert envelopes Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 4286-4289. DOI: 10.1109/ICASSP.2010.5495668  0.68
2010 Povey D, Burget L, Agarwal M, Akyazi P, Feng K, Ghoshal A, Glembek O, Goel NK, Karafiát M, Rastrow A, Rose RC, Schwarz P, Thomas S. Subspace gaussian mixture models for speech recognition Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 4330-4333. DOI: 10.1109/ICASSP.2010.5495662  0.361
2010 Burget L, Schwarz P, Agarwal M, Akyazi P, Feng K, Ghoshal A, Glembek O, Goel N, Karafiát M, Povey D, Rastrow A, Rose RC, Thomas S. Multilingual acoustic modeling for speech recognition based on subspace Gaussian mixture models Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 4334-4337. DOI: 10.1109/ICASSP.2010.5495646  0.339
2010 Ganapathy S, Thomas S, Hermansky H. Comparison of modulation features for phoneme recognition Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 5038-5041. DOI: 10.1109/ICASSP.2010.5495057  0.701
2009 Ganapathy S, Thomas S, Hermansky H. Modulation frequency features for phoneme recognition in noisy speech. The Journal of the Acoustical Society of America. 125: EL8-12. PMID 19173383 DOI: 10.1121/1.3040022  0.737
2009 Thomas S, Ganapathy S, Hermansky H. Phoneme recognition using spectral envelope and modulation frequency features Icassp, Ieee International Conference On Acoustics, Speech and Signal Processing - Proceedings. 4453-4456. DOI: 10.1109/ICASSP.2009.4960618  0.69
2009 Ganapathy S, Thomas S, Hermansky H. Temporal envelope subtraction for robust speech recognition using modulation spectrum Proceedings of the 2009 Ieee Workshop On Automatic Speech Recognition and Understanding, Asru 2009. 164-169. DOI: 10.1109/ASRU.2009.5372922  0.707
2009 Ganapathy S, Thomas S, Motlicek P, Hermansky H. Applications of signal analysis using autoregressive models for amplitude modulation Ieee Workshop On Applications of Signal Processing to Audio and Acoustics. 341-344. DOI: 10.1109/ASPAA.2009.5346495  0.627
2008 Thomas S, Ganapathy S, Hermansky H. Recognition of reverberant speech using frequency domain linear prediction Ieee Signal Processing Letters. 15: 681-684. DOI: 10.1109/Lsp.2008.2002708  0.723
Show low-probability matches.