Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition

Hu, YuchenChen, ChenLi, RuizheZhu, QiushiChng, Eng Siong2025-03-162025-03-162023-06-04Hu, Y, Chen, C, Li, R, Zhu, Q & Chng, E S 2023, Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE Explore, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23. https://doi.org/10.48550/ARXIV.2302.11362, https://doi.org/10.1109/ICASSP49357.2023.10096615conference978-1-7281-6328-4978-1-7281-6327-7Bibtex: https://doi.org/10.48550/arxiv.2302.11362ORCID: /0000-0003-2512-845X/work/136882761https://hdl.handle.net/2164/25148This research is supported by National Research Foundation Singapore under its AI Singapore Programme (Award Number: AISG2-100E-2022-10).5730539engGradient remedyMulti-task learningspeech enhancementnoise-robust speech recognitiongradient interferenceQA75 Electronic computers. Computer scienceQA75Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech RecognitionConference item10.48550/ARXIV.2302.11362