| Contentvec: An improved self-supervised speech representation by disentangling speakers K Qian, Y Zhang, H Gao, J Ni, CI Lai, D Cox, M Hasegawa-Johnson, ... International Conference on Machine Learning, 18003-18017, 2022 | 62 | 2022 |
| Unsupervised text-to-speech synthesis by unsupervised automatic speech recognition J Ni, L Wang, H Gao, K Qian, Y Zhang, S Chang, M Hasegawa-Johnson arXiv preprint arXiv:2203.15796, 2022 | 29 | 2022 |
| Wavprompt: Towards few-shot spoken language understanding with frozen language models H Gao, J Ni, K Qian, Y Zhang, S Chang, M Hasegawa-Johnson arXiv preprint arXiv:2203.15863, 2022 | 20 | 2022 |
| Zero-Shot Cross-Lingual Phonetic Recognition with External Language Embedding. H Gao, J Ni, Y Zhang, K Qian, S Chang, M Hasegawa-Johnson Interspeech, 1304-1308, 2021 | 13 | 2021 |
| Seamless equal accuracy ratio for inclusive CTC speech recognition H Gao, X Wang, S Kang, R Mina, D Issa, J Harvill, L Sari, ... Speech Communication 136, 76-83, 2022 | 8 | 2022 |
| Hierarchical multi-armed bandits for discovering hidden populations S Kumar, H Gao, C Wang, KCC Chang, H Sundaram Proceedings of the 2019 IEEE/ACM International Conference on Advances in …, 2019 | 7 | 2019 |
| Decision tree Thompson sampling for mining hidden populations through attributed search S Kumar, H Gao, C Wang, KCC Chang, H Sundaram Social Network Analysis and Mining 12 (1), 6, 2022 | 6 | 2022 |
| G2PU: Grapheme-To-Phoneme Transducer with Speech Units H Gao, M Hasegawa-Johnson, CD Yoo ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | | 2024 |
| Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction E Yoon, HS Yoon, D Gowda, SH Eom, D Kim, J Harvill, H Gao, ... arXiv preprint arXiv:2308.08442, 2023 | | 2023 |
| Listen, Decipher and Sign: Toward Unsupervised Speech-to-Sign Language Recognition L Wang, J Ni, H Gao, J Li, KC Chang, X Fan, J Wu, M Hasegawa-Johnson, ... Findings of the Association for Computational Linguistics: ACL 2023, 6785-6800, 2023 | | 2023 |
| Speak, Decipher and Sign: Toward Unsupervised Speech-to-Sign Language Recognition W Liming, J Ni, H Gao, J Li, KC Chang, X Fan, J Wu, ... The 61st Annual Meeting of the Association for Computational Linguistics, 2023 | | 2023 |
| Domain Generalization for Language-Independent Automatic Speech Recognition H Gao, J Ni, Y Zhang, K Qian, S Chang, M Hasegawa-Johnson Frontiers in Artificial Intelligence 5, 806274, 2022 | | 2022 |
| Improving Self-Supervised Speech Representations by Disentangling Speakers. K Qian, Y Zhang, H Gao, J Ni, CI Lai, DD Cox, M Hasegawa-Johnson, ... CoRR, 2022 | | 2022 |
| Improving multilingual speech recognition systems H Gao University of Illinois at Urbana-Champaign, 2021 | | 2021 |
| Mining Hidden Populations through Attributed Search S Kumar, H Gao, C Wang, H Sundaram, KCC Chang arXiv preprint arXiv:1905.04505, 2019 | | 2019 |
| Macross: Activity Mining based on Metapath Guided Cross-Modal Embedding Y Zhang, H Gao, J Han | | |
Mark Hasegawa-JohnsonProfessor of Electrical and Computer Engineering, University of IllinoisVerified email at illinois.edu
