Speech Enhancement Using Multi-stage Self-attentive Temporal Convolutional Networks

Abstract

Multi-stage learning is an effective technique to invoke multiple deep-learning modules sequentially. This paper applies multi-stage learning to speech enhancement by using a multi-stage structure, where each stage comprises a self-attention (SA) block followed by stacks of temporal convolutional network (TCN) blocks with doubling dilation factors. Each stage generates a prediction that is refined in a subsequent stage. A fusion block is inserted at the input of later stages to re-inject original information. The resulting multi-stage speech enhancement system, in short, multi-stage SA-TCN, is compared with state-of-the-art deep-learning speech enhancement methods using the LibriSpeech and VCTK data sets. The multi-stage SA-TCN system's hyper-parameters are fine-tuned, and the impact of the SA block, the fusion block and the number of stages are determined. The use of a multi-stage SA-TCN system as a front-end for automatic speech recognition systems is investigated as well. It is show

Stats

• citations76
• S2 citations—
• github stars0
• HF likes0
• heat score14.15
• arxiv keylin2021speech

Related papers

• Monaural Speech Enhancement Using A Multi-branch Temporal Convolutional Network (2019)3.58
• FB-MSTCN: A Full-band Single-channel Speech Enhancement Method Based On Multi-scale Temporal Convolutional Network (2022)6.77
• State-of-the-art Speech Recognition Using Multi-stream Self-attention With Dilated 1D Convolutions (2019)11.93
• Incorporating Multi-target In Multi-stage Speech Enhancement Model For Better Generalization (2021)0.00
• Self-attention Networks For Connectionist Temporal Classification In Speech Recognition (2019)14.55
• TFCN: Temporal-frequential Convolutional Network For Single-channel Speech Enhancement (2022)0.00
• Vsanet: Real-time Speech Enhancement Based On Voice Activity Detection And Causal Spatial Attention (2023)5.24
• Multi-loss Convolutional Network With Time-frequency Attention For Speech Enhancement (2023)0.00