Quantifying bias in automatic speech recognition S Feng, O Kudina, BM Halpern, O Scharenborg arXiv preprint arXiv:2103.15122, 2021 | 95 | 2021 |
Automatic Speech Assessment for People with Aphasia Using TDNN-BLSTM with Multi-Task Learning. Y Qin, T Lee, S Feng, APH Kong Interspeech, 3418-3422, 2018 | 29 | 2018 |
Combining adversarial training and disentangled speech representation for robust zero-resource subword modeling S Feng, T Lee, Z Peng INTERSPEECH, 1093--1097, 2019 | 22 | 2019 |
How phonotactics affect multilingual and zero-shot asr performance S Feng, P Żelasko, L Moro-Velázquez, A Abavisani, ... ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 18 | 2021 |
The effectiveness of time stretching for enhancing dysarthric speech for improved dysarthric speech recognition L Prananta, BM Halpern, S Feng, O Scharenborg arXiv preprint arXiv:2201.04908, 2022 | 15 | 2022 |
Efficient neural music generation MWY Lam, Q Tian, T Li, Z Yin, S Feng, M Tu, Y Ji, R Xia, M Ma, X Song, ... Advances in Neural Information Processing Systems 36, 2024 | 14 | 2024 |
Discovering phonetic inventories with crosslingual automatic speech recognition P Żelasko, S Feng, LM Velazquez, A Abavisani, S Bhati, O Scharenborg, ... Computer Speech & Language 74, 101358, 2022 | 13 | 2022 |
Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation S Feng, P Żelasko, L Moro-Velázquez, O Scharenborg INTERSPEECH 2021, 1534--1538, 2021 | 12 | 2021 |
Improving Cross-Lingual Knowledge Transferability Using Multilingual TDNN-BLSTM with Language-Dependent Pre-Final Layer. S Feng, T Lee INTERSPEECH, 2439-2443, 2018 | 12 | 2018 |
PolyVoice: Language Models for Speech to Speech Translation Q Dong, Z Huang, Q Tian, C Xu, T Ko, Y Zhao, S Feng, T Li, K Wang, ... arXiv preprint arXiv:2306.02982, 2023 | 11 | 2023 |
Towards inclusive automatic speech recognition S Feng, BM Halpern, O Kudina, O Scharenborg Computer Speech & Language 84, 101567, 2024 | 10 | 2024 |
Exploiting cross-lingual speaker and phonetic diversity for unsupervised subword modeling S Feng, T Lee IEEE/ACM Transactions on Audio, Speech, and Language Processing 27 (12 …, 2019 | 9 | 2019 |
Improving unsupervised subword modeling via disentangled speech representation learning and transformation S Feng, T Lee INTERSPEECH, 281--285, 2019 | 9 | 2019 |
Adversarial multi-task deep features and unsupervised back-end adaptation for language recognition Z Peng, S Feng, T Lee ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 8 | 2019 |
Disordered speech assessment using kullback-leibler divergence features with multi-task acoustic modeling Y Liu, Y Qin, S Feng, T Lee, PC Ching 2018 11th International Symposium on Chinese Spoken Language Processing …, 2018 | 8 | 2018 |
Low-resource automatic speech recognition and error analyses of oral cancer speech BM Halpern, S Feng, R van Son, M van den Brekel, O Scharenborg Speech Communication 141, 14-27, 2022 | 7 | 2022 |
Show and speak: Directly synthesize spoken description of images X Wang, S Feng, J Zhu, M Hasegawa-Johnson, O Scharenborg ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 7 | 2021 |
Mixture factorized auto-encoder for unsupervised hierarchical deep factorization of speech signal Z Peng, S Feng, T Lee ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 7 | 2020 |
Exploiting language-mismatched phoneme recognizers for unsupervised acoustic modeling S Feng, T Lee, H Wang 2016 10th International Symposium on Chinese Spoken Language Processing …, 2016 | 7 | 2016 |
Exploiting Speaker and Phonetic Diversity of Mismatched Language Resources for Unsupervised Subword Modeling. S Feng, T Lee INTERSPEECH, 2673-2677, 2018 | 6 | 2018 |