| Self-critical sequence training for image captioning SJ Rennie, E Marcheret, Y Mroueh, J Ross, V Goel Proceedings of the IEEE conference on computer vision and pattern …, 2017 | 1871 | 2017 |
| Data augmentation for deep neural network acoustic modeling X Cui, V Goel, B Kingsbury IEEE/ACM Transactions on Audio, Speech, and Language Processing 23 (9), 1469 …, 2015 | 473 | 2015 |
| Deep multimodal learning for audio-visual speech recognition Y Mroueh, E Marcheret, V Goel 2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015 | 260 | 2015 |
| Minimum Bayes-risk automatic speech recognition V Goel, WJ Byrne Computer Speech & Language 14 (2), 115-135, 2000 | 241 | 2000 |
| Privacy-sensitive speech model creation via aggregation of multiple user models AR Lee, P Novak, PA Olsen, V Goel US Patent 9,424,836, 2016 | 192 | 2016 |
| Mcgan: Mean and covariance feature matching gan Y Mroueh, T Sercu, V Goel International conference on machine learning, 2527-2535, 2017 | 147 | 2017 |
| Sparse maximum a posteriori (map) adaption V Goel, PA Olsen, SJ Rennie, J Huang US Patent 8,972,258, 2015 | 97 | 2015 |
| Dominant frequency analysis of EEG reveals brain's response during injury and recovery V Goel, AM Brambrink, A Baykal, RC Koehler, DF Hanley, NV Thakor IEEE transactions on biomedical engineering 43 (11), 1083-1092, 1996 | 90 | 1996 |
| Method and apparatus to estimate downtime and cost of downtime in an information technology infrastructure J Walsh, A Rockall, A Sudarsky US Patent App. 10/109,277, 2003 | 84 | 2003 |
| Segmental minimum Bayes-risk decoding for automatic speech recognition V Goel, S Kumar, W Byrne IEEE transactions on Speech and Audio Processing 12 (3), 234-249, 2004 | 77 | 2004 |
| Annealed dropout training of deep networks SJ Rennie, V Goel, S Thomas 2014 IEEE Spoken Language Technology Workshop (SLT), 159-164, 2014 | 76 | 2014 |
| Natural language system and method based on unisolated performance metric S Deligne, Y Gao, V Goel, HK Kuo, C Wu US Patent 7,574,358, 2009 | 68 | 2009 |
| Dense prediction on sequences with time-dilated convolutions for speech recognition T Sercu, V Goel arXiv preprint arXiv:1611.09288, 2016 | 65 | 2016 |
| Data augmentation for deep convolutional neural network acoustic modeling X Cui, V Goel, B Kingsbury 2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015 | 60 | 2015 |
| Advances in very deep convolutional neural networks for LVCSR T Sercu, V Goel arXiv preprint arXiv:1604.01792, 2016 | 58 | 2016 |
| Method and system for using a statistical language model and an action classifier in parallel with grammar for better handling of out-of-grammar utterances V Goel, R Gopinath, EE Jan, K Visweswariah US Patent 8,396,713, 2013 | 58 | 2013 |
| Subspace constrained Gaussian mixture models for speech recognition S Axelrod, V Goel, RA Gopinath, PA Olsen, K Visweswariah IEEE Transactions on speech and audio processing 13 (6), 1144-1160, 2005 | 55 | 2005 |
| Syllable-A promising recognition unit for LVCSR A Ganapathiraju, V Goel, J Picone, A Corrada, G Doddington, K Kirchhoff, ... 1997 IEEE Workshop on Automatic Speech Recognition and Understanding …, 1997 | 48 | 1997 |
| Discriminative estimation of subspace constrained gaussian mixture models for speech recognition S Axelrod, V Goel, R Gopinath, P Olsen, K Visweswariah IEEE transactions on audio, speech, and language processing 15 (1), 172-189, 2006 | 40 | 2006 |
| Segmental minimum Bayes-risk ASR voting strategies V Goel, S Kumar, W Byrne Sixth International Conference on Spoken Language Processing, 2000 | 40 | 2000 |
