DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lee, Dongheon, Choi, Jung-Woo
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912582314491904
author Lee, Dongheon
Choi, Jung-Woo
author_facet Lee, Dongheon
Choi, Jung-Woo
contents This paper presents a framework for universal sound separation and polyphonic audio classification, addressing the challenges of separating and classifying individual sound sources in a multichannel mixture. The proposed framework, DeFT-Mamba, utilizes the dense frequency-time attentive network (DeFTAN) combined with Mamba to extract sound objects, capturing the local time-frequency relations through gated convolution block and the global time-frequency relations through position-wise Hybrid Mamba. DeFT-Mamba surpasses existing separation and classification networks by a large margin, particularly in complex scenarios involving in-class polyphony. Additionally, a classification-based source counting method is introduced to identify the presence of multiple sources, outperforming conventional threshold-based approaches. Separation refinement tuning is also proposed to improve performance further. The proposed framework is trained and tested on a multichannel universal sound separation dataset developed in this work, designed to mimic realistic environments with moving sources and varying onsets and offsets of polyphonic events.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12413
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification
Lee, Dongheon
Choi, Jung-Woo
Audio and Speech Processing
Sound
This paper presents a framework for universal sound separation and polyphonic audio classification, addressing the challenges of separating and classifying individual sound sources in a multichannel mixture. The proposed framework, DeFT-Mamba, utilizes the dense frequency-time attentive network (DeFTAN) combined with Mamba to extract sound objects, capturing the local time-frequency relations through gated convolution block and the global time-frequency relations through position-wise Hybrid Mamba. DeFT-Mamba surpasses existing separation and classification networks by a large margin, particularly in complex scenarios involving in-class polyphony. Additionally, a classification-based source counting method is introduced to identify the presence of multiple sources, outperforming conventional threshold-based approaches. Separation refinement tuning is also proposed to improve performance further. The proposed framework is trained and tested on a multichannel universal sound separation dataset developed in this work, designed to mimic realistic environments with moving sources and varying onsets and offsets of polyphonic events.
title DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2409.12413