Saved in:
Bibliographic Details
Main Authors: Xie, Xuemai, Wang, Xianrui, Zhang, Liyuan, Yang, Yichen, Makino, Shoji
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.02382
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918153254076416
author Xie, Xuemai
Wang, Xianrui
Zhang, Liyuan
Yang, Yichen
Makino, Shoji
author_facet Xie, Xuemai
Wang, Xianrui
Zhang, Liyuan
Yang, Yichen
Makino, Shoji
contents Among numerous blind source separation (BSS) methods, convolutive transfer function-based multichannel non-negative matrix factorization (CTF-MNMF) has demonstrated strong performance in highly reverberant environments by modeling multi-frame correlations of delayed source signals. However, its practical deployment is hindered by the high computational cost associated with the iterative projection (IP) update rule, which requires matrix inversion for each source. To address this issue, we propose an efficient variant of CTF-MNMF that integrates iterative source steering (ISS), a matrix inversion-free update rule for separation filters. Experimental results show that the proposed method achieves comparable or superior separation performance to the original CTF-MNMF, while significantly reducing the computational complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02382
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accelerated Convolutive Transfer Function-Based Multichannel NMF Using Iterative Source Steering
Xie, Xuemai
Wang, Xianrui
Zhang, Liyuan
Yang, Yichen
Makino, Shoji
Sound
Audio and Speech Processing
Among numerous blind source separation (BSS) methods, convolutive transfer function-based multichannel non-negative matrix factorization (CTF-MNMF) has demonstrated strong performance in highly reverberant environments by modeling multi-frame correlations of delayed source signals. However, its practical deployment is hindered by the high computational cost associated with the iterative projection (IP) update rule, which requires matrix inversion for each source. To address this issue, we propose an efficient variant of CTF-MNMF that integrates iterative source steering (ISS), a matrix inversion-free update rule for separation filters. Experimental results show that the proposed method achieves comparable or superior separation performance to the original CTF-MNMF, while significantly reducing the computational complexity.
title Accelerated Convolutive Transfer Function-Based Multichannel NMF Using Iterative Source Steering
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2510.02382