University of Aberdeen logo

AURA - Aberdeen University Research Archive

 

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

Simple item page
dc.contributor.authorHu, Yuchen
dc.contributor.authorChen, Chen
dc.contributor.authorLi, Ruizhe
dc.contributor.authorZhu, Qiushi
dc.contributor.authorChng, Eng Siong
dc.contributor.institutionUniversity of Aberdeen.Computing Scienceen
dc.contributor.institutionUniversity of Aberdeen.Computational Linguistics at Aberdeenen
dc.date.accessioned2025-03-16T00:19:37Z
dc.date.available2025-03-16T00:19:37Z
dc.date.embargoedUntil2025-03-16
dc.date.issued2023-06-04
dc.descriptionThis research is supported by National Research Foundation Singapore under its AI Singapore Programme (Award Number: AISG2-100E-2022-10).en
dc.format.extent5
dc.format.extent730539
dc.identifier254605679
dc.identifier12049ed2-8b64-4a91-88f9-8fac39da81fe
dc.identifier85166349940
dc.identifier.citationHu, 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/ICASSP49357.2023.10096615en
dc.identifier.citationconferenceen
dc.identifier.doi10.48550/ARXIV.2302.11362
dc.identifier.isbn978-1-7281-6328-4
dc.identifier.isbn978-1-7281-6327-7
dc.identifier.otherBibtex: https://doi.org/10.48550/arxiv.2302.11362
dc.identifier.otherORCID: /0000-0003-2512-845X/work/136882761
dc.identifier.urihttps://hdl.handle.net/2164/25148
dc.language.isoeng
dc.publisherIEEE Explore
dc.relation.ispartofICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)en
dc.subjectGradient remedyen
dc.subjectMulti-task learningen
dc.subjectspeech enhancementen
dc.subjectnoise-robust speech recognitionen
dc.subjectgradient interferenceen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subject.lccQA75en
dc.titleGradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognitionen
dc.typeConference itemen

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Hu_etal_IEEE_Gradient_Remedy_For_AAM.pdf
Size:
713.42 KB
Format:
Adobe Portable Document Format
Download

Collections

All research