TFSWA-ResUNet: music source separation with time–frequency sequence and shifted window attention-based ResUNet

Abstract CNN-based UNet is a widely employed network architecture for music source separation (MSS). Meanwhile, spectrogram features of music audio, which consist of both time and frequency information, are commonly used as inputs for MSS tasks. CNN-based UNet models in the spectrogram domain still...

Полное описание

Библиографические подробности

Главные авторы:	Zhenyu Yao, Yuping Su, Honghong Yang, Yumei Zhang, Xiaojun Wu
Формат:	Artigo
Язык:	Inglês
Опубликовано:	SpringerOpen 2025-09-01
Серии:	EURASIP Journal on Advances in Signal Processing
Предметы:	Music source separation ResUNet Time sequence attention Frequency sequence attention Shifted window attention
Online-ссылка:	https://doi.org/10.1186/s13634-025-01249-0
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!