Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Jihyun, Kindt, Stijn, Madhu, Nilesh, Kang, Hong-Goo
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.09819
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910487269081088
author Kim, Jihyun
Kindt, Stijn
Madhu, Nilesh
Kang, Hong-Goo
author_facet Kim, Jihyun
Kindt, Stijn
Madhu, Nilesh
Kang, Hong-Goo
contents Ad-hoc distributed microphone environments, where microphone locations and numbers are unpredictable, present a challenge to traditional deep learning models, which typically require fixed architectures. To tailor deep learning models to accommodate arbitrary array configurations, the Transform-Average-Concatenate (TAC) layer was previously introduced. In this work, we integrate TAC layers with dual-path transformers for speech separation from two simultaneous talkers in realistic settings. However, the distributed nature makes it hard to fuse information across microphones efficiently. Therefore, we explore the efficacy of blindly clustering microphones around sources of interest prior to enhancement. Experimental results show that this deep cluster-informed approach significantly improves the system's capacity to cope with the inherent variability observed in ad-hoc distributed microphone environments.
format Preprint
id arxiv_https___arxiv_org_abs_2406_09819
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments
Kim, Jihyun
Kindt, Stijn
Madhu, Nilesh
Kang, Hong-Goo
Audio and Speech Processing
Ad-hoc distributed microphone environments, where microphone locations and numbers are unpredictable, present a challenge to traditional deep learning models, which typically require fixed architectures. To tailor deep learning models to accommodate arbitrary array configurations, the Transform-Average-Concatenate (TAC) layer was previously introduced. In this work, we integrate TAC layers with dual-path transformers for speech separation from two simultaneous talkers in realistic settings. However, the distributed nature makes it hard to fuse information across microphones efficiently. Therefore, we explore the efficacy of blindly clustering microphones around sources of interest prior to enhancement. Experimental results show that this deep cluster-informed approach significantly improves the system's capacity to cope with the inherent variability observed in ad-hoc distributed microphone environments.
title Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments
topic Audio and Speech Processing
url https://arxiv.org/abs/2406.09819