| CNNBiF - CNN-based Bigram Features for Named Entity Recognition. | 0 | 0.34 | 2021 |
| Embedding-Based Speaker Adaptive Training Of Deep Neural Networks | 3 | 0.39 | 2017 |
| McGan: Mean and Covariance Feature Matching GAN. | 16 | 0.63 | 2017 |
| Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition. | 1 | 0.37 | 2016 |
| Annealed Dropout Trained Maxout Networks For Improved Lvcsr | 1 | 0.39 | 2015 |
| Data Augmentation For Deep Convolutional Neural Network Acoustic Modeling | 6 | 0.55 | 2015 |
| Maximum likelihood nonlinear transformations based on deep neural networks | 0 | 0.34 | 2015 |
| Evaluating Deep Scattering Spectra With Deep Neural Networks On Large Scale Spontaneous Speech Task | 1 | 0.35 | 2015 |
| Detecting Audio-Visual Synchrony Using Deep Neural Networks | 4 | 0.41 | 2015 |
| Multimodal Retrieval With Asymmetrically Weighted Truncated-SVD Canonical Correlation Analysis. | 1 | 0.35 | 2015 |
| Deep Multimodal Learning For Audio-Visual Speech Recognition | 27 | 0.84 | 2015 |
| Scattering vs. discrete cosine transform features in visual speech processing. | 0 | 0.34 | 2015 |
| Random Maxout Features | 1 | 0.35 | 2015 |
| Data Augmentation for Deep Neural Network Acoustic Modeling | 41 | 1.93 | 2014 |
| Improving deep neural network acoustic modeling for audio corpus indexing under the IARPA babel program. | 3 | 0.42 | 2014 |
| Reduction of acoustic model training time and required data passes via stochastic approaches to maximum likelihood and discriminative training | 0 | 0.34 | 2014 |
| Annealed dropout training of deep networks | 18 | 0.73 | 2014 |
| Regularized feature-space discriminative adaptation for robust ASR. | 0 | 0.34 | 2014 |
| Deep Order Statistic Networks | 8 | 0.63 | 2014 |
| A Difference of Convex Functions Approach to Large-Scale Log-Linear Model Estimation | 1 | 0.34 | 2013 |
| Direct product based deep belief networks for automatic speech recognition. | 1 | 0.36 | 2013 |
| Combining stochastic average gradient and Hessian-free optimization for sequence training of deep neural networks | 4 | 0.44 | 2013 |
| State Of The Art Discriminative Training Of Subspace Constrained Gaussian Mixture Models In Big Training Corpora | 0 | 0.34 | 2013 |
| Front-end feature transforms with context filtering for speaker adaptation | 1 | 0.36 | 2011 |
| Sparse Maximum A Posteriori adaptation. | 3 | 0.41 | 2011 |
| Discriminative training for full covariance models | 2 | 0.40 | 2011 |
| Trends and advances in speech recognition | 2 | 0.50 | 2011 |
| Refactoring acoustic models using variational density approximation | 3 | 0.51 | 2009 |
| Refactoring Acoustic Models Using Variational Expectation-Maximization | 4 | 0.48 | 2009 |
| A fast, accurate approximation to log likelihood of Gaussian mixture models | 0 | 0.34 | 2009 |
| Acoustic Modeling Using Exponential Families | 2 | 0.41 | 2009 |
| Compacting Discriminative Feature Space Transforms For Embedded Devices | 0 | 0.34 | 2009 |
| Discriminative Estimation of Subspace Constrained Gaussian Mixture Models for Speech Recognition | 16 | 0.99 | 2007 |
| Active learning with minimum expected error for spoken language understanding | 11 | 0.92 | 2005 |
| Exploiting unlabeled data using multiple classifiers for improved natural language call-routing | 7 | 0.77 | 2005 |
| Subspace constrained Gaussian mixture models for speech recognition. | 22 | 2.04 | 2005 |
| Language Model Estimation For Optimizing End-To-End Performance Of A Natural Language Call Routing System | 5 | 0.56 | 2005 |
| Improving end-to-end performance of call classification through data confusion reduction and model tolerance enhancement | 2 | 0.49 | 2005 |
| Efficient likelihood computation in multi-stream HMM based audio-visual speech recognition | 1 | 0.39 | 2004 |
| Stochastic gradient adaptation of front-end parameters | 1 | 0.35 | 2004 |
| Task adaptation of acoustic and language models based on large quantities of data | 4 | 0.56 | 2004 |
| Conditional maximum likelihood estimation for improving annotation performance of n-gram models incorporating stochastic finite state grammars | 2 | 0.48 | 2004 |
| Segmental Minimum Bayes-Risk Decoding For Automatic Speech Recognition | 30 | 1.78 | 2004 |
| Large vocabulary conversational speech recognition with a subspace constraint on inverse covariance matrices | 6 | 0.85 | 2003 |
| Discriminative estimation of subspace precision and mean (SPAM) models | 8 | 0.84 | 2003 |
| Toward domain-independent conversational speech recognition | 10 | 1.05 | 2003 |
| Large vocabulary conversational speech recognition with the extended maximum likelihood linear transformation (EMLLT) model | 9 | 0.89 | 2002 |
| Adaptation experiments on the SPINE database with the Extended Maximum Likelihood Linear Transformation (EMLLT) model | 1 | 0.36 | 2002 |
| Confidence based lattice segmentation and minimum Bayes-risk decoding | 4 | 0.61 | 2001 |
| Recent advances in speech recognition system for IBM DARPA communicator | 9 | 1.02 | 2001 |
