On deep multi-view representation learning W Wang, R Arora, K Livescu, J Bilmes International conference on machine learning, 1083-1092, 2015 | 1082 | 2015 |
Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application W Wang, MA Carreira-Perpinán arXiv preprint arXiv:1309.1541, 2013 | 328 | 2013 |
Distributed optimization of deeply nested systems M Carreira-Perpinan, W Wang Artificial Intelligence and Statistics, 10-19, 2014 | 218 | 2014 |
Deep convolutional acoustic word embeddings using word-pair side information H Kamper, W Wang, K Livescu 2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016 | 188 | 2016 |
Deep variational canonical correlation analysis W Wang, X Yan, H Lee, K Livescu arXiv preprint arXiv:1610.03454, 2016 | 165 | 2016 |
Deep multilingual correlation for improved word embeddings A Lu, W Wang, M Bansal, K Gimpel, K Livescu Proceedings of the 2015 conference of the North American chapter of the …, 2015 | 161 | 2015 |
Unsupervised learning of acoustic features via deep canonical correlation analysis W Wang, R Arora, K Livescu, JA Bilmes 2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015 | 158 | 2015 |
Unsupervised pre-training of bidirectional speech encoders via masked reconstruction W Wang, Q Tang, K Livescu ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 110 | 2020 |
Nonparametric canonical correlation analysis T Michaeli, W Wang, K Livescu International conference on machine learning, 1967-1976, 2016 | 99 | 2016 |
Multi-view recurrent neural acoustic word embeddings W He, W Wang, K Livescu arXiv preprint arXiv:1611.04496, 2016 | 97 | 2016 |
Stochastic optimization for deep CCA via nonlinear orthogonal iterations W Wang, R Arora, K Livescu, N Srebro 2015 53rd Annual Allerton Conference on Communication, Control, and …, 2015 | 80 | 2015 |
Manifold blurring mean shift algorithms for manifold denoising W Wang, MA Carreira-Perpinán 2010 IEEE Computer Society Conference on Computer Vision and Pattern …, 2010 | 68 | 2010 |
R-crnn: Region-based convolutional recurrent neural network for audio event detection CC Kao, W Wang, M Sun, C Wang arXiv preprint arXiv:1808.06627, 2018 | 64 | 2018 |
Memory and communication efficient distributed stochastic optimization with minibatch prox J Wang, W Wang, N Srebro Conference on Learning Theory, 1882-1919, 2017 | 60 | 2017 |
Large-scale approximate kernel canonical correlation analysis W Wang, K Livescu arXiv preprint arXiv:1511.04773, 2015 | 60 | 2015 |
Semi-supervised ASR by end-to-end self-training Y Chen, W Wang, C Wang arXiv preprint arXiv:2001.09128, 2020 | 57 | 2020 |
Multimodal and multi-view models for emotion recognition G Aguilar, V Rozgić, W Wang, C Wang arXiv preprint arXiv:1906.10198, 2019 | 49 | 2019 |
Lexicon-free fingerspelling recognition from video: Data, models, and signer adaptation T Kim, J Keane, W Wang, H Tang, J Riggle, G Shakhnarovich, D Brentari, ... Computer Speech & Language 46, 209-232, 2017 | 49 | 2017 |
Raw waveform based end-to-end deep convolutional network for spatial localization of multiple acoustic sources H Sundar, W Wang, M Sun, C Wang ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 46 | 2020 |
An investigation of phone-based subword units for end-to-end speech recognition W Wang, G Wang, A Bhatnagar, Y Zhou, C Xiong, R Socher arXiv preprint arXiv:2004.04290, 2020 | 46 | 2020 |