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...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Zhenyu Yao, Yuping Su, Honghong Yang, Yumei Zhang, Xiaojun Wu
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	SpringerOpen 2025-09-01
סדרה:	EURASIP Journal on Advances in Signal Processing
נושאים:	Music source separation ResUNet Time sequence attention Frequency sequence attention Shifted window attention
גישה מקוונת:	https://doi.org/10.1186/s13634-025-01249-0
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!