Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation

Lecture Notes in Networks and Systems (LNNS,volume 882); The 13th Conference on Information Technology and Its Applications (CITA 2024) ; pp: 99-110.

Đã lưu trong:

Bibliografiske detaljer
Những tác giả chính:	Ha, Minh Tan, Fhadli, Muhammad, Nguyen, Kim Quoc, Vu, Quang Duc
Format:	Bài viết
Sprog:	English
Udgivet:	Springer Nature 2024
Fag:	The suggested method is tested and assessed on a conventional dataset Model is relearned, enhanced
Online adgang:	https://elib.vku.udn.vn/handle/123456789/4272 https://doi.org/10.1007/978-3-031-74127-2_9
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!

Thư viện lưu trữ:	Trường Đại học Công nghệ Thông tin và Truyền thông Việt Hàn - Đại học Đà Nẵng

id	oai:elib.vku.udn.vn:123456789-4272
record_format	dspace
spelling	oai:elib.vku.udn.vn:123456789-42722024-12-06T03:38:08Z Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation Ha, Minh Tan Fhadli, Muhammad Nguyen, Kim Quoc Vu, Quang Duc The suggested method is tested and assessed on a conventional dataset Model is relearned, enhanced Lecture Notes in Networks and Systems (LNNS,volume 882); The 13th Conference on Information Technology and Its Applications (CITA 2024) ; pp: 99-110. In this work, the pre-trained model of the self-attention framework is proposed for single-channel speech separation. Firstly, all layers in the pre-trained self-attention framework are frozen. The model is then retrained through three stages using the scheduling mechanism for learning rates and the layers of the framework are unlocked following the schedule. This way, the model is relearned, enhanced, and updated from previous knowledge. This is an effective way to improve the advanced model performance while significantly reducing the time and cost of a training model. This method is beneficial in applying existing models to perform a similar task or enhancing model performance. In this strategy, the pre-trained system outperforms the non-pre-trained system since the following phases of the model’s training repurpose characteristics extracted through the previously trained early phases. The suggested method is tested and assessed on a conventional dataset. The findings from experiments suggest that the methodology has higher performance than the baseline framework and outperforms current methods for the monaural speech separation task. 2024-12-04T04:04:20Z 2024-12-04T04:04:20Z 2024-11 Working Paper 978-3-031-74126-5 https://elib.vku.udn.vn/handle/123456789/4272 https://doi.org/10.1007/978-3-031-74127-2_9 en application/pdf Springer Nature
institution	Trường Đại học Công nghệ Thông tin và Truyền thông Việt Hàn - Đại học Đà Nẵng
collection	DSpace
language	English
topic	The suggested method is tested and assessed on a conventional dataset Model is relearned, enhanced
spellingShingle	The suggested method is tested and assessed on a conventional dataset Model is relearned, enhanced Ha, Minh Tan Fhadli, Muhammad Nguyen, Kim Quoc Vu, Quang Duc Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation
description	Lecture Notes in Networks and Systems (LNNS,volume 882); The 13th Conference on Information Technology and Its Applications (CITA 2024) ; pp: 99-110.
format	Working Paper
author	Ha, Minh Tan Fhadli, Muhammad Nguyen, Kim Quoc Vu, Quang Duc
author_facet	Ha, Minh Tan Fhadli, Muhammad Nguyen, Kim Quoc Vu, Quang Duc
author_sort	Ha, Minh Tan
title	Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation
title_short	Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation
title_full	Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation
title_fullStr	Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation
title_full_unstemmed	Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation
title_sort	pre-trained self-attention framework: an efficient mechanism for source separation
publisher	Springer Nature
publishDate	2024
url	https://elib.vku.udn.vn/handle/123456789/4272 https://doi.org/10.1007/978-3-031-74127-2_9
_version_	1849202065031561216

Pre-trained Self-Attention Framework: An Efficient Mechanism for Source Separation

Lignende værker