| 2021 | EMNLP | CNNBiF: CNN-based Bigram Features for Named Entity Recognition. | Chul Sung, Vaibhava Goel, Etienne Marcheret, Steven J. Rennie, David Nahamoo |
| 2020 | EMNLP | Unsupervised Adaptation of Question Answering Systems via Generative Self-training. | Steven J. Rennie, Etienne Marcheret, Neil Mallinar, David Nahamoo, Vaibhava Goel |
| 2017 | AISTATS | Co-Occurring Directions Sketching for Approximate Matrix Multiply. | Youssef Mroueh, Etienne Marcheret, Vaibhava Goel |
| 2017 | CVPR | Self-Critical Sequence Training for Image Captioning. | Steven J. Rennie, Etienne Marcheret, Youssef Mroueh, Jerret Ross, Vaibhava Goel |
| 2017 | ICASSP | Noisy objective functions based on the f-divergence. | Markus Nubaum-Thom, Ralf Schlter, Vaibhava Goel, Hermann Ney |
| 2017 | ICML | McGan: Mean and Covariance Feature Matching GAN. | Youssef Mroueh, Tom Sercu, Vaibhava Goel |
| 2017 | Interspeech | Embedding-Based Speaker Adaptive Training of Deep Neural Networks. | Xiaodong Cui, Vaibhava Goel, George Saon |
| 2016 | ICASSP | Efficient non-linear feature adaptation using Maxout networks. | Steven J. Rennie, Xiaodong Cui, Vaibhava Goel |
| 2016 | Interspeech | Acoustic Modeling Using Bidirectional Gated Recurrent Convolutional Units. | Markus Nubaum-Thom, Jia Cui, Bhuvana Ramabhadran, Vaibhava Goel |
| 2016 | Interspeech | Advances in Very Deep Convolutional Neural Networks for LVCSR. | Tom Sercu, Vaibhava Goel |
| 2015 | ICASSP | Maximum likelihood nonlinear transformations based on deep neural networks. | Xiaodong Cui, Vaibhava Goel |
| 2015 | ICASSP | Data augmentation for deep convolutional neural network acoustic modeling. | Xiaodong Cui, Vaibhava Goel, Brian Kingsbury |
| 2015 | ICASSP | Evaluating Deep Scattering Spectra with deep neural networks on large scale spontaneous speech task. | Petr Fousek, Pierre L. Dognin, Vaibhava Goel |
| 2015 | ICASSP | Deep multimodal learning for Audio-Visual Speech Recognition. | Youssef Mroueh, Etienne Marcheret, Vaibhava Goel |
| 2015 | ICASSP | Annealed dropout trained maxout networks for improved LVCSR. | Steven J. Rennie, Pierre L. Dognin, Xiaodong Cui, Vaibhava Goel |
| 2015 | Interspeech | Detecting audio-visual synchrony using deep neural networks. | Etienne Marcheret, Gerasimos Potamianos, Josef Vopicka, Vaibhava Goel |
| 2014 | ICASSP | Data Augmentation for deep neural network acoustic modeling. | Xiaodong Cui, Vaibhava Goel, Brian Kingsbury |
| 2014 | ICASSP | Reduction of acoustic model training time and required data passes via stochastic approaches to maximum likelihood and discriminative training. | Petr Novk, Roman Otec, Antonio Lee, Vaibhava Goel |
| 2014 | ICASSP | A family of discriminative training criteria based on the F-divergence for deep neural networks. | Markus Nubaum-Thom, Xiaodong Cui, Ralf Schlter, Vaibhava Goel, Hermann Ney |
| 2014 | ICASSP | Deep Scattering Spectrum with deep neural networks. | Vijayaditya Peddinti, Tara N. Sainath, Shay Maymon, Bhuvana Ramabhadran, David Nahamoo, Vaibhava Goel |
| 2014 | Interspeech | Improving deep neural network acoustic modeling for audio corpus indexing under the IARPA babel program. | Xiaodong Cui, Brian Kingsbury, Jia Cui, Bhuvana Ramabhadran, Andrew Rosenberg, Mohammad Sadegh Rasooli, Owen Rambow, Nizar Habash, Vaibhava Goel |
| 2014 | Interspeech | Regularized feature-space discriminative adaptation for robust ASR. | Takashi Fukuda, Osamu Ichikawa, Masafumi Nishimura, Steven J. Rennie, Vaibhava Goel |
| 2013 | ASRU | Combining stochastic average gradient and Hessian-free optimization for sequence training of deep neural networks. | Pierre L. Dognin, Vaibhava Goel |
| 2013 | ICASSP | Direct product based deep belief networks for automatic speech recognition. | Petr Fousek, Steven J. Rennie, Pierre L. Dognin, Vaibhava Goel |
| 2013 | ICASSP | State of the art discriminative training of subspace constrained Gaussian mixture models in big training corpora. | Jing Huang, Peder A. Olsen, Vaibhava Goel |
| 2013 | Interspeech | Mixtures of Bayesian joint factor analyzers for noise robust automatic speech recognition. | Xiaodong Cui, Vaibhava Goel, Brian Kingsbury |
| 2013 | Interspeech | Adaptive stereo-based stochastic mapping. | Shay Maymon, Pierre L. Dognin, Xiaodong Cui, Vaibhava Goel |
| 2013 | Interspeech | Restoration of clipped signals with application to speech recognition. | Shay Maymon, Etienne Marcheret, Vaibhava Goel |
| 2012 | ICASSP | A framework for unsupervised transfer learning and application to dialog decision classification. | Etienne Marcheret, Om D. Deshmukh, Vaibhava Goel, Jir Navrtil |
| 2012 | ICASSP | Affine invariant sparse maximum a posteriori adaptation. | Peder A. Olsen, Jing Huang, Steven J. Rennie, Vaibhava Goel |
| 2012 | Interspeech | Sparse Bayesian Factor Analysis for Stereo-based Stochastic Mapping. | Xiaodong Cui, Mohamed Afify, George Saon, Vaibhava Goel |
| 2012 | Interspeech | Investigating Performance of the Discriminative Methods for Long-Term Speaker Adaptation. | Danning Jiang, Dimitri Kanevsky, Vaibhava Goel, Yong Qin |
| 2011 | ASRU | Sparse Maximum A Posteriori adaptation. | Peder A. Olsen, Jing Huang, Vaibhava Goel, Steven J. Rennie |
| 2011 | ICASSP | Front-end feature transforms with context filtering for speaker adaptation. | Jing Huang, Karthik Visweswariah, Peder A. Olsen, Vaibhava Goel |
| 2011 | ICASSP | Discriminative training for full covariance models. | Peder A. Olsen, Vaibhava Goel, Steven J. Rennie |
| 2011 | ICASSP | Exemplar-based Sparse Representation phone identification features. | Tara N. Sainath, David Nahamoo, Bhuvana Ramabhadran, Dimitri Kanevsky, Vaibhava Goel, Parikshit M. Shah |
| 2010 | Interspeech | Restructuring exponential family mixture models. | Pierre L. Dognin, John R. Hershey, Vaibhava Goel, Peder A. Olsen |
| 2010 | Interspeech | Incorporating sparse representation phone identification features in automatic speech recognition using exponential families. | Vaibhava Goel, Tara N. Sainath, Bhuvana Ramabhadran, Peder A. Olsen, David Nahamoo, Dimitri Kanevsky |
| 2010 | Interspeech | Modeling posterior probabilities using the linear exponential family. | Peder A. Olsen, Vaibhava Goel, Charles A. Micchelli, John R. Hershey |
| 2009 | ASRU | Optimal quantization and bit allocation for compressing large discriminative feature space transforms. | Etienne Marcheret, Vaibhava Goel, Peder A. Olsen |
| 2009 | ICASSP | A fast, accurate approximation to log likelihood of Gaussian mixture models. | Pierre L. Dognin, Vaibhava Goel, John R. Hershey, Peder A. Olsen |
| 2009 | ICASSP | Refactoring acoustic models using variational density approximation. | Pierre L. Dognin, John R. Hershey, Vaibhava Goel, Peder A. Olsen |
| 2009 | Interspeech | Refactoring acoustic models using variational expectation-maximization. | Pierre L. Dognin, John R. Hershey, Vaibhava Goel, Peder A. Olsen |
| 2009 | Interspeech | Acoustic modeling using exponential families. | Vaibhava Goel, Peder A. Olsen |
| 2009 | Interspeech | Compacting discriminative feature space transforms for embedded devices. | Etienne Marcheret, Jia-Yu Chen, Petr Fousek, Peder A. Olsen, Vaibhava Goel |
| 2008 | ICASSP | Optimizing speech recognition grammars using a measure of similarity between hidden Markov models. | Binit Mohanty, John R. Hershey, Peder A. Olsen, Suleyman Serdar Kozat, Vaibhava Goel |
| 2007 | Interspeech | A data visualization and analysis method for natural language call routing system design. | Hong-Kwang Jeff Kuo, Vaibhava Goel |
| 2006 | Interspeech | On designing context sensitive language models for spoken dialog systems. | Vaibhava Goel, Ramesh A. Gopinath |
| 2005 | ICASSP | Language Model Estimation for Optimizing End-to-end Performance of a Natural Language Call Routing System. | Vaibhava Goel, Hong-Kwang Kuo, Sabine Deligne, Cheng Wu |
| 2005 | Interspeech | Active learning with minimum expected error for spoken language understanding. | Hong-Kwang Jeff Kuo, Vaibhava Goel |
| 2005 | Interspeech | Exploiting unlabeled data using multiple classifiers for improved natural language call-routing. | Ruhi Sarikaya, Hong-Kwang Jeff Kuo, Vaibhava Goel, Yuqing Gao |
| 2005 | Interspeech | Improving end-to-end performance of call classification through data confusion reduction and model tolerance enhancement. | Cheng Wu, Xiang Li, Hong-Kwang Jeff Kuo, E. E. Jan, Vaibhava Goel, David M. Lubensky |
| 2004 | Interspeech | Stochastic gradient adaptation of front-end parameters. | Sreeram Balakrishnan, Karthik Visweswariah, Vaibhava Goel |
| 2004 | Interspeech | Conditional maximum likelihood estimation for improving annotation performance of n-gram models incorporating stochastic finite state grammars. | Vaibhava Goel |
| 2004 | Interspeech | Efficient likelihood computation in multi-stream HMM based audio-visual speech recognition. | Etienne Marcheret, Stephen M. Chu, Vaibhava Goel, Gerasimos Potamianos |
| 2004 | Interspeech | Task adaptation of acoustic and language models based on large quantities of data. | Karthik Visweswariah, Ramesh A. Gopinath, Vaibhava Goel |
| 2003 | Interspeech | Large vocabulary conversational speech recognition with a subspace constraint on inverse covariance matrices. | Scott Axelrod, Vaibhava Goel, Brian Kingsbury, Karthik Visweswariah, Ramesh A. Gopinath |
| 2003 | Interspeech | Discriminative estimation of subspace precision and mean (SPAM) models. | Vaibhava Goel, Scott Axelrod, Ramesh A. Gopinath, Peder A. Olsen, Karthik Visweswariah |
| 2003 | Interspeech | Toward domain-independent conversational speech recognition. | Brian Kingsbury, Lidia Mangu, George Saon, Geoffrey Zweig, Scott Axelrod, Vaibhava Goel, Karthik Visweswariah, Michael Picheny |
| 2002 | ICASSP | Rapid adaptation with linear combinations of rank-one matrices. | Vaibhava Goel, Karthik Visweswariah, Ramesh Gopinath |
| 2002 | ICASSP | Adaptation experiments on the SPINE database with the Extended Maximum Likelihood Linear Transformation (EMLLT) model. | Ramesh Gopinath, Vaibhava Goel, Karthik Visweswariah, Peder A. Olsen |
| 2002 | ICASSP | Structuring linear transforms for adaptation using training time information. | Karthik Visweswariah, Vaibhava Goel, Ramesh Gopinath |
| 2002 | Interspeech | Large vocabulary conversational speech recognition with the extended maximum likelihood linear transformation (EMLLT) model. | Jing Huang, Vaibhava Goel, Ramesh Gopinath, Brian Kingsbury, Peder A. Olsen, Karthik Visweswariah |
| 2001 | Interspeech | Recent advances in speech recognition system for IBM DARPA communicator. | Yuqing Gao, Hakan Erdogan, Yongxin Li, Vaibhava Goel, Michael Picheny |
| 2001 | Interspeech | Confidence based lattice segmentation and minimum Bayes-risk decoding. | Vaibhava Goel, Shankar Kumar, William Byrne |
| 2000 | Interspeech | Segmental minimum Bayes-risk ASR voting strategies. | Vaibhava Goel, Shankar Kumar, William Byrne |
| 1999 | Interspeech | Task dependent loss functions in speech recognition: a* search over recognition lattices. | Vaibhava Goel, William Byrne |
| 1998 | ICASSP | LVCSR rescoring with modified loss functions: a decision theoretic perspective. | Vaibhava Goel, William Byrne, Sanjeev Khudanpur |
| 1995 | ICASSP | Quantification of injury-related EEG signal changes using Itakura distance measure. | Xuan Kong, Vaibhava Goel, Nitish V. Thakor |