Mon-3-11-2 Atss-Net: Target Speaker Separation via Attention-based Neural Network

Tingle Li(Duke Kunshan University), Qingjian Lin(SEIT, Sun Yat-sen University), Yuanyuan Bao(Duke Kunshan University) and Ming Li(Duke Kunshan University)
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.
Student Information

Student Events

Travel Grants