| An unsupervised autoregressive model for speech representation learning YA Chung, WN Hsu, H Tang, J Glass Interspeech, 146-150, 2019 | 223 | 2019 |
| Audio word2vec: Unsupervised learning of audio segment representations using sequence-to-sequence autoencoder YA Chung, CC Wu, CH Shen, HY Lee, LS Lee Interspeech, 765-769, 2016 | 164 | 2016 |
| Speech2vec: A sequence-to-sequence framework for learning word embeddings from speech YA Chung, J Glass Interspeech, 811-815, 2018 | 145 | 2018 |
| Generative pre-training for speech with autoregressive predictive coding YA Chung, J Glass ICASSP, 3497-3501, 2020 | 99 | 2020 |
| Disentangling correlated speaker and noise for speech synthesis via data augmentation and adversarial factorization WN Hsu, Y Zhang, RJ Weiss, YA Chung, Y Wang, Y Wu, J Glass ICASSP, 5901-5905, 2019 | 94 | 2019 |
| Semi-supervised training for improving data efficiency in end-to-end speech synthesis YA Chung, Y Wang, WN Hsu, Y Zhang, RJ Skerry-Ryan ICASSP, 6940-6944, 2019 | 90 | 2019 |
| Cost-aware pre-training for multiclass cost-sensitive deep learning YA Chung, HT Lin, SW Yang IJCAI, 1411-1417, 2016 | 75 | 2016 |
| Supervised and unsupervised transfer learning for question answering YA Chung, HY Lee, J Glass NAACL-HLT, 1585-1594, 2018 | 71 | 2018 |
| Unsupervised cross-modal alignment of speech and text embedding spaces YA Chung, WH Weng, S Tong, J Glass NeurIPS, 7365-7375, 2018 | 70 | 2018 |
| Learning deep representations of medical images using siamese CNNs with application to content-based image retrieval YA Chung, WH Weng NIPS Workshop on Machine Learning for Health, 2017 | 67 | 2017 |
| AST: Audio spectrogram transformer Y Gong, YA Chung, J Glass Interspeech, 571-575, 2021 | 64 | 2021 |
| libact: Pool-based active learning in python YY Yang, SC Lee, YA Chung, TE Wu, SA Chen, HT Lin arXiv preprint arXiv:1710.00379, 2017 | 46 | 2017 |
| Vector-quantized autoregressive predictive coding YA Chung, H Tang, J Glass Interspeech, 3760-3764, 2020 | 42 | 2020 |
| Unsupervised learning of audio segment representations using sequence-to-sequence recurrent neural networks YA Chung, CC Wu, CH Shen, HY Lee, LS Lee Interspeech, 765-769, 2016 | 35 | 2016 |
| Improved speech representations with multi-target autoregressive predictive coding YA Chung, J Glass ACL, 2353-2358, 2020 | 33 | 2020 |
| Towards unsupervised speech-to-text translation YA Chung, WH Weng, S Tong, J Glass ICASSP, 7170-7174, 2019 | 32 | 2019 |
| w2v-BERT: Combining contrastive learning and masked language modeling for self-supervised speech pre-training YA Chung, Y Zhang, W Han, CC Chiu, J Qin, R Pang, Y Wu ASRU, 244-250, 2021 | 29 | 2021 |
| Non-autoregressive predictive coding for learning speech representations from local dependencies AH Liu, YA Chung, J Glass Interspeech, 3730-3734, 2021 | 25 | 2021 |
| SPLAT: Speech-language joint pre-training for spoken language understanding YA Chung, C Zhu, M Zeng NAACL-HLT, 1897-1907, 2021 | 23 | 2021 |
| Towards transfer learning for end-to-end speech synthesis from deep pre-trained language models W Fang, YA Chung, J Glass arXiv preprint arXiv:1906.07307, 2019 | 22 | 2019 |
James GlassMIT Computer Science and Artificial Intelligence LaboratoryVerified email at mit.edu
