publications
2019
2018
-
Disentangling by Partitioning: A Representation Learning Framework for Multimodal Sensory Data arXiv preprint arXiv:1805.11264 2018 [Paper]
-
Unsupervised Representation Learning of Speech for Dialect Identification IEEE Workshop on Spoken Language Technology Workshop (SLT) 2018 [Paper]
-
Unsupervised Adaptation with Interpretable Disentangled Representation for Distant Conversational Speech Recognition In Interspeech 2018 [Paper]
-
A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition In Interspeech 2018 [Paper]
-
A Noise-Robust Self-Adaptive Multitarget Speaker Detection System In International Conference on Pattern Recognition 2018
2017
-
Automatic Speech Recognition of Arabic Multi-Genre Broadcast Media In IEEE Workshop on Automatic Speech Recognition and Understanding Workshop (ASRU) 2017
2016
-
Neural Attention for Learning to Rank Questions in Community Question Answering In International Conference on Computational Linguistics (COLING) 2016 [Paper]
-
A Prioritized Grid Long Short-Term Memory RNN for Speech Recognition In IEEE Workshop on Spoken Language Technology Workshop (SLT) 2016 [Paper]
-
Development of the MIT ASR System for the 2016 Arabic Multi-Genre Broadcast Challenge In IEEE Workshop on Spoken Language Technology Workshop (SLT) 2016 [Paper]
-
SLS at SemEval-2016 Task 3: Neural-based approaches for ranking in community question answering In International Workshop on Semantic Evaluation (SemEval) 2016 [Paper]
-
Exploiting Depth and Highway Connections in Convolutional Recurrent Deep Neural Networks for Speech Recognition In Interspeech 2016 [Paper]
-
Multi-Channel Speech Recognition: LSTMs All the Way Through In The 4th CHiME Speech Separation and Recognition Challenge 2016 [Paper]
2015
-
Enhancing Automatically Discovered Multi-Level Acoustic Patterns Considering Context Consistency with Applications in Spoken Term Detection In International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015 [Paper]