SMRU: Split-and-Merge Recurrent-based UNet for Acoustic Echo Cancellation and Noise Suppression

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Zhihang, Li, Andong, Chen, Rilin, Zhang, Hao, Yu, Meng, Zhou, Yi, Yu, Dong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929685229731840
author Sun, Zhihang
Li, Andong
Chen, Rilin
Zhang, Hao
Yu, Meng
Zhou, Yi
Yu, Dong
author_facet Sun, Zhihang
Li, Andong
Chen, Rilin
Zhang, Hao
Yu, Meng
Zhou, Yi
Yu, Dong
contents The proliferation of deep neural networks has spawned the rapid development of acoustic echo cancellation and noise suppression, and plenty of prior arts have been proposed, which yield promising performance. Nevertheless, they rarely consider the deployment generality in different processing scenarios, such as edge devices, and cloud processing. To this end, this paper proposes a general model, termed SMRU, to cover different application scenarios. The novelty lies in two-fold. First, a multi-scale band split layer and band merge layer are proposed to effectively fuse local frequency bands for lower complexity modeling. Besides, by simulating the multi-resolution feature modeling characteristic of the classical UNet structure, a novel recurrent-dominated UNet is devised. It consists of multiple variable frame rate blocks, each of which involves the causal time down-/up-sampling layer with varying compression ratios and the dual-path structure for inter- and intra-band modeling. The model is configured from 50 M/s to 6.8 G/s in terms of MACs, and the experimental results show that the proposed approach yields competitive or even better performance over existing baselines, and has the full potential to adapt to more general scenarios with varying complexity requirements.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11175
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SMRU: Split-and-Merge Recurrent-based UNet for Acoustic Echo Cancellation and Noise Suppression
Sun, Zhihang
Li, Andong
Chen, Rilin
Zhang, Hao
Yu, Meng
Zhou, Yi
Yu, Dong
Sound
Audio and Speech Processing
The proliferation of deep neural networks has spawned the rapid development of acoustic echo cancellation and noise suppression, and plenty of prior arts have been proposed, which yield promising performance. Nevertheless, they rarely consider the deployment generality in different processing scenarios, such as edge devices, and cloud processing. To this end, this paper proposes a general model, termed SMRU, to cover different application scenarios. The novelty lies in two-fold. First, a multi-scale band split layer and band merge layer are proposed to effectively fuse local frequency bands for lower complexity modeling. Besides, by simulating the multi-resolution feature modeling characteristic of the classical UNet structure, a novel recurrent-dominated UNet is devised. It consists of multiple variable frame rate blocks, each of which involves the causal time down-/up-sampling layer with varying compression ratios and the dual-path structure for inter- and intra-band modeling. The model is configured from 50 M/s to 6.8 G/s in terms of MACs, and the experimental results show that the proposed approach yields competitive or even better performance over existing baselines, and has the full potential to adapt to more general scenarios with varying complexity requirements.
title SMRU: Split-and-Merge Recurrent-based UNet for Acoustic Echo Cancellation and Noise Suppression
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2406.11175