CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jiang, Chengqian, Zhang, Jie, Yan, Haoyin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908786435817472
author Jiang, Chengqian
Zhang, Jie
Yan, Haoyin
author_facet Jiang, Chengqian
Zhang, Jie
Yan, Haoyin
contents Distributed microphone array (DMA) is a promising next-generation platform for speech interaction, where speech enhancement (SE) is still required to improve the speech quality in noisy cases. Existing SE methods usually first gather raw waveforms at a fusion center (FC) from all devices and then design a multi-microphone model, causing high bandwidth and energy costs. In this work, we propose a \emph{Compress-and-Send Network (CaSNet)} for resource-constrained DMAs, where one microphone serves as the FC and reference. Each of other devices encodes the measured raw data into a feature matrix, which is then compressed by singular value decomposition (SVD) to produce a more compact representation. The received features at the FC are aligned via cross window query with respect to the reference, followed by neural decoding to yield spatially coherent enhanced speech. Experiments on multiple datasets show that the proposed CaSNet can save the data amount with a negligible impact on the performance compared to the uncompressed case. The reproducible code is available at https://github.com/Jokejiangv/CaSNet.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17711
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays
Jiang, Chengqian
Zhang, Jie
Yan, Haoyin
Sound
Artificial Intelligence
Audio and Speech Processing
Distributed microphone array (DMA) is a promising next-generation platform for speech interaction, where speech enhancement (SE) is still required to improve the speech quality in noisy cases. Existing SE methods usually first gather raw waveforms at a fusion center (FC) from all devices and then design a multi-microphone model, causing high bandwidth and energy costs. In this work, we propose a \emph{Compress-and-Send Network (CaSNet)} for resource-constrained DMAs, where one microphone serves as the FC and reference. Each of other devices encodes the measured raw data into a feature matrix, which is then compressed by singular value decomposition (SVD) to produce a more compact representation. The received features at the FC are aligned via cross window query with respect to the reference, followed by neural decoding to yield spatially coherent enhanced speech. Experiments on multiple datasets show that the proposed CaSNet can save the data amount with a negligible impact on the performance compared to the uncompressed case. The reproducible code is available at https://github.com/Jokejiangv/CaSNet.
title CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2601.17711