Atss-Net: Target Speaker Separation via Attention-based Neural Network

2020/05/19 by Li, Tingle, Lin, Qingjian, Bao, Yuanyuan +1 · 1 citation
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2005.09200

Abstract

Recently, Convolutional Neural Network (CNN) and Long short-term memory (LSTM) based models have been introduced to deep learning-based target speaker separation. In this paper, we propose an Attention-based neural network (Atss-Net) in the spectrogram domain for the task. It allows the network to compute the correlation between each feature parallelly, and using shallower layers to extract more features, compared with the CNN-LSTM architecture. Experimental results show that our Atss-Net yields better performance than the VoiceFilter, although it only contains half of the parameters. Furthermore, our proposed model also demonstrates promising performance in speech enhancement.

Cited by

• Sounding that Object: Interactive Object-Aware Image to Audio Generation

Related

• Sams-Net: A Sliced Attention-based Neural Network for Music Source Separation
• VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
• Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement
• An Efficient Speech Separation Network Based on Recurrent Fusion Dilated Convolution and Channel Attention
• VSANet: Real-time Speech Enhancement Based on Voice Activity Detection and Causal Spatial Attention