Learning in supervised and unsupervised environments
Autoencoders and dimentionality reduction
- Attention-based models for speech recognition with Dzmitry Bahdanau, Dmitriy Serdyuk, Kyunghyun Cho, Yoshua Bengio, NeurIPS, 2015.
- End-to-end attention-based large vocabulary speech recognition with Dzmitry Bahdanau, Dmitriy Serdyuk, Philemon Brakel, Yoshua Bengio, ICASSP, 2016.
- Regularizing Neural Networks by Penalizing Confident Output Distributions with Gabriel Pereyra, George Tucker, Lukasz Kaiser, Geoffrey E. Hinton, ICLR (Workshop) 2017
- State-of-the-art speech recognition with sequence-to-sequence models with Chung-Cheng Chiu, Tara N Sainath, Yonghui Wu, Rohit Prabhavalkar, Patrick Nguyen, Zhifeng Chen, Anjuli Kannan, Ron J Weiss, Kanishka Rao, Ekaterina Gonina, Navdeep Jaitly, Bo Li, Michiel Bacchiani, ICASSP, 2018.
- Robust 3d action recognition with random occupancy patterns with Jiang Wang, Zicheng Liu, Zhuoyuan Chen, Ying Wu, ECCV, 2012.
- Unsupervised speech representation learning using wavenet autoencoders with Ron J Weiss, Samy Bengio, Aäron van den Oord, IEEE/ACM Transactions on Audio, Speech and Language Processing, 2019.
- Towards Better Decoding and Language Model Integration in Sequence to Sequence Models with Navdeep Jaitly, ISCA, 2017.
- Sequence-to-sequence models can directly translate foreign speech with Ron J Weiss, Navdeep Jaitly, Ying Wu, Zhuoyuan Chen, ISCA, 2017.