Saved in:
Bibliographic Details
Main Authors: Hsu, Yicheng, Chen, Ssuhan, Bai, Mingsian R.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.16850
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909087694848000
author Hsu, Yicheng
Chen, Ssuhan
Bai, Mingsian R.
author_facet Hsu, Yicheng
Chen, Ssuhan
Bai, Mingsian R.
contents A robust multichannel speaker diarization and separation system is proposed by exploiting the spatio-temporal activity of the speakers. The system is realized in a hybrid architecture that combines the array signal processing units and the deep learning units. For speaker diarization, a spatial coherence matrix across time frames is computed based on the whitened relative transfer functions (wRTFs) of the microphone array. This serves as a robust feature for subsequent machine learning without the need for prior knowledge of the array configuration. A computationally efficient Spatial Activity-driven Speaker Diarization network (SASDnet) is constructed to estimate the speaker activity directly from the spatial coherence matrix. For speaker separation, we propose the Global and Local Activity-driven Speaker Extraction network (GLASEnet) to separate speaker signals via speaker-specific global and local spatial activity functions. The local spatial activity functions depend on the coherence between the wRTFs of each time-frequency bin and the target speaker-dominant bins. The global spatial activity functions are computed from the global spatial coherence functions based on frequency-averaged local spatial activity functions. Experimental results have demonstrated superior speaker, diarization, counting, and separation performance achieved by the proposed system with low computational complexity compared to the pre-selected baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2401_16850
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spatial-Temporal Activity-Informed Diarization and Separation
Hsu, Yicheng
Chen, Ssuhan
Bai, Mingsian R.
Audio and Speech Processing
Sound
A robust multichannel speaker diarization and separation system is proposed by exploiting the spatio-temporal activity of the speakers. The system is realized in a hybrid architecture that combines the array signal processing units and the deep learning units. For speaker diarization, a spatial coherence matrix across time frames is computed based on the whitened relative transfer functions (wRTFs) of the microphone array. This serves as a robust feature for subsequent machine learning without the need for prior knowledge of the array configuration. A computationally efficient Spatial Activity-driven Speaker Diarization network (SASDnet) is constructed to estimate the speaker activity directly from the spatial coherence matrix. For speaker separation, we propose the Global and Local Activity-driven Speaker Extraction network (GLASEnet) to separate speaker signals via speaker-specific global and local spatial activity functions. The local spatial activity functions depend on the coherence between the wRTFs of each time-frequency bin and the target speaker-dominant bins. The global spatial activity functions are computed from the global spatial coherence functions based on frequency-averaged local spatial activity functions. Experimental results have demonstrated superior speaker, diarization, counting, and separation performance achieved by the proposed system with low computational complexity compared to the pre-selected baselines.
title Spatial-Temporal Activity-Informed Diarization and Separation
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2401.16850