Jasha Droppo
Jasha Droppo
Verifierad e-postadress på amazon.com
TitelCiteras avÅr
The Microsoft 2017 conversational speech recognition system
W Xiong, L Wu, F Alleva, J Droppo, X Huang, A Stolcke
2018 IEEE international conference on acoustics, speech and signal …, 2018
3362018
Achieving human parity in conversational speech recognition
W Xiong, J Droppo, X Huang, F Seide, M Seltzer, A Stolcke, D Yu, ...
arXiv preprint arXiv:1610.05256, 2016
3242016
1-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns
F Seide, H Fu, J Droppo, G Li, D Yu
Fifteenth Annual Conference of the International Speech Communication …, 2014
2712014
An introduction to computational networks and the computational network toolkit
D Yu, A Eversole, M Seltzer, K Yao, Z Huang, B Guenter, O Kuchaiev, ...
Microsoft Technical Report MSR-TR-2014–112, 2014
2582014
Method and apparatus for multi-sensory speech enhancement
Z Liu, MJ Sinclair, A Acero, XD Huang, JG Droppo, L Deng, Z Zhang, ...
US Patent 7,447,630, 2008
2392008
Method and apparatus for multi-sensory speech enhancement
Z Liu, MJ Sinclair, A Acero, XD Huang, JG Droppo, L Deng, Z Zhang, ...
US Patent 7,447,630, 2008
2332008
Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion
L Deng, J Droppo, A Acero
IEEE Transactions on Speech and Audio Processing 13 (3), 412-421, 2005
1992005
Multi-task learning in deep neural networks for improved phoneme recognition
ML Seltzer, J Droppo
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
1892013
Uncertainty decoding with SPLICE for noise robust speech recognition
J Droppo, A Acero, L Deng
2002 IEEE International Conference on Acoustics, Speech, and Signal …, 2002
1822002
High-performance robust speech recognition using stereo training data
L Deng, A Acero, L Jiang, J Droppo, X Huang
2001 IEEE International Conference on Acoustics, Speech, and Signal …, 2001
1782001
Evaluation of the SPLICE algorithm on the Aurora2 database
J Droppo, L Deng, A Acero
Seventh European Conference on Speech Communication and Technology, 2001
1742001
Including the category of environmental noise when processing speech signals
JG Droppo, A Acero, L Deng
US Patent 6,959,276, 2005
1402005
Enhancement of log mel power spectra of speech using a phase-sensitive model of the acoustic environment and sequential estimation of the corrupting noise
L Deng, J Droppo, A Acero
IEEE Transactions on Speech and Audio Processing 12 (2), 133-143, 2004
1362004
Recursive estimation of nonstationary noise using iterative stochastic approximation for robust speech recognition
L Deng, J Droppo, A Acero
IEEE Transactions on Speech and Audio Processing 11 (6), 568-580, 2003
1302003
An introduction to computational networks and the computational network toolkit
A Agarwal, E Akchurin, C Basoglu, G Chen, S Cyphers, J Droppo, ...
Tech. Rep. MSR-TR-2014-112, 2014
1132014
Environmental robustness
J Droppo, A Acero
springer handbook of speech processing, 653-680, 2008
902008
Air-and bone-conductive integrated microphones for robust speech detection and enhancement
Y Zheng, Z Liu, Z Zhang, M Sinclair, J Droppo, L Deng, A Acero, X Huang
2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE …, 2003
852003
Noise adaptive training for robust automatic speech recognition
O Kalinli, ML Seltzer, J Droppo, A Acero
IEEE Transactions on Audio, Speech, and Language Processing 18 (8), 1889-1901, 2010
842010
Estimating cepstrum of speech under the presence of noise using a joint prior of static and dynamic features
L Deng, J Droppo, A Acero
IEEE Transactions on Speech and Audio Processing 12 (3), 218-233, 2004
822004
Method of noise reduction based on dynamic aspects of speech
L Deng, JG Droppo, A Acero
US Patent 7,107,210, 2006
812006
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20