PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech Enhancement

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Zizhen, Wang, Junyu, Li, Ruili, Shen, Fei, Xuan, Xi
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909514665558016
author Lin, Zizhen
Wang, Junyu
Li, Ruili
Shen, Fei
Xuan, Xi
author_facet Lin, Zizhen
Wang, Junyu
Li, Ruili
Shen, Fei
Xuan, Xi
contents Single-channel speech enhancement is a challenging ill-posed problem focused on estimating clean speech from degraded signals. Existing studies have demonstrated the competitive performance of combining convolutional neural networks (CNNs) with Transformers in speech enhancement tasks. However, existing frameworks have not sufficiently addressed computational efficiency and have overlooked the natural multi-scale distribution of the spectrum. Additionally, the potential of CNNs in speech enhancement has yet to be fully realized. To address these issues, this study proposes a Deep Separable Dilated Dense Block (DSDDB) and a Group Prime Kernel Feedforward Channel Attention (GPFCA) module. Specifically, the DSDDB introduces higher parameter and computational efficiency to the Encoder/Decoder of existing frameworks. The GPFCA module replaces the position of the Conformer, extracting deep temporal and frequency features of the spectrum with linear complexity. The GPFCA leverages the proposed Group Prime Kernel Feedforward Network (GPFN) to integrate multi-granularity long-range, medium-range, and short-range receptive fields, while utilizing the properties of prime numbers to avoid periodic overlap effects. Experimental results demonstrate that PrimeK-Net, proposed in this study, achieves state-of-the-art (SOTA) performance on the VoiceBank+Demand dataset, reaching a PESQ score of 3.61 with only 1.41M parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19906
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech Enhancement
Lin, Zizhen
Wang, Junyu
Li, Ruili
Shen, Fei
Xuan, Xi
Audio and Speech Processing
Sound
Single-channel speech enhancement is a challenging ill-posed problem focused on estimating clean speech from degraded signals. Existing studies have demonstrated the competitive performance of combining convolutional neural networks (CNNs) with Transformers in speech enhancement tasks. However, existing frameworks have not sufficiently addressed computational efficiency and have overlooked the natural multi-scale distribution of the spectrum. Additionally, the potential of CNNs in speech enhancement has yet to be fully realized. To address these issues, this study proposes a Deep Separable Dilated Dense Block (DSDDB) and a Group Prime Kernel Feedforward Channel Attention (GPFCA) module. Specifically, the DSDDB introduces higher parameter and computational efficiency to the Encoder/Decoder of existing frameworks. The GPFCA module replaces the position of the Conformer, extracting deep temporal and frequency features of the spectrum with linear complexity. The GPFCA leverages the proposed Group Prime Kernel Feedforward Network (GPFN) to integrate multi-granularity long-range, medium-range, and short-range receptive fields, while utilizing the properties of prime numbers to avoid periodic overlap effects. Experimental results demonstrate that PrimeK-Net, proposed in this study, achieves state-of-the-art (SOTA) performance on the VoiceBank+Demand dataset, reaching a PESQ score of 3.61 with only 1.41M parameters.
title PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech Enhancement
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2502.19906