Select, answer and explain: Interpretable multi-hop reading comprehension over multiple documents M Tu, K Huang, G Wang, J Huang, X He, B Zhou Proceedings of the AAAI conference on artificial intelligence 34 (05), 9073-9080, 2020 | 195 | 2020 |
Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs M Tu, G Wang, J Huang, Y Tang, X He, B Zhou Proceedings of the 57th Annual Meeting of the Association for Computational …, 2019 | 187 | 2019 |
Simulating dysarthric speech for training data augmentation in clinical speech applications Y Jiao, M Tu, V Berisha, J Liss 2018 IEEE international conference on acoustics, speech and signal …, 2018 | 87 | 2018 |
Accent Identification by Combining Deep Neural Networks and Recurrent Neural Networks Trained on Long and Short Term Features. Y Jiao, M Tu, V Berisha, JM Liss Interspeech, 2388-2392, 2016 | 87 | 2016 |
Multiple instance learning based on graph neural networks M Tu, J Huang, X He, B Zhou ICML 2019 workshop on Learning and Reasoning with Graph-Structured …, 2019 | 78* | 2019 |
Speaker-invariant affective representation learning via adversarial training H Li, M Tu, J Huang, S Narayanan, P Georgiou ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 68 | 2020 |
Speech enhancement based on deep neural networks with skip connections M Tu, X Zhang 2017 IEEE international conference on acoustics, speech and signal …, 2017 | 61 | 2017 |
Interpretable Objective Assessment of Dysarthric Speech Based on Deep Neural Networks. M Tu, V Berisha, J Liss Interspeech, 1849-1853, 2017 | 60 | 2017 |
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 | 56 | 2024 |
Investigating the role of L1 in automatic pronunciation evaluation of L2 speech M Tu, A Grabek, J Liss, V Berisha Proc. Interspeech 2018, 1636-1640, 2018 | 45 | 2018 |
The relationship between perceptual disturbances in dysarthric speech and automatic speech recognition performance M Tu, A Wisler, V Berisha, JM Liss The Journal of the Acoustical Society of America 140 (5), EL416-EL422, 2016 | 42 | 2016 |
Ranking the parameters of deep neural networks using the fisher information M Tu, V Berisha, M Woolf, J Seo, Y Cao 2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016 | 39 | 2016 |
Reducing the model order of deep neural networks using information theory M Tu, V Berisha, Y Cao, J Seo 2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 93-98, 2016 | 37 | 2016 |
Convex weighting criteria for speaking rate estimation Y Jiao, V Berisha, M Tu, J Liss IEEE/ACM transactions on audio, speech, and language processing 23 (9), 1421 …, 2015 | 35 | 2015 |
I4U submission to NIST SRE 2018: Leveraging from a decade of shared experiences KA Lee, V Hautamaki, T Kinnunen, H Yamamoto, K Okabe, V Vestman, ... arXiv preprint arXiv:1904.07386, 2019 | 23 | 2019 |
Towards adversarial learning of speaker-invariant representation for speech emotion recognition M Tu, Y Tang, J Huang, X He, B Zhou arXiv preprint arXiv:1903.09606, 2019 | 21 | 2019 |
Online speaking rate estimation using recurrent neural networks Y Jiao, M Tu, V Berisha, J Liss 2016 ieee international conference on acoustics, speech and signal …, 2016 | 21 | 2016 |
Seed-asr: Understanding diverse speech and contexts with llm-based speech recognition Y Bai, J Chen, J Chen, W Chen, Z Chen, C Ding, L Dong, Q Dong, Y Du, ... arXiv preprint arXiv:2407.04675, 2024 | 14 | 2024 |
Articulation constrained learning with application to speech emotion recognition M Shah, M Tu, V Berisha, C Chakrabarti, A Spanias EURASIP journal on audio, speech, and music processing 2019, 1-17, 2019 | 14 | 2019 |
Objective assessment of pathological speech using distribution regression M Tu, V Berisha, J Liss 2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017 | 13 | 2017 |