Atss-Net: Target Speaker Separation via Attention-based Neural Network
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.
Submitted to Interspeech 2020
References in corpus (9)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Attention U-Net: Learning Where to Look for the Pancreas
- Deep Learning using Rectified Linear Units (ReLU)
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- Deep attractor network for single-microphone speaker separation
- AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale
- Voice and accompaniment separation in music using self-attention convolutional neural network
- LaFurca: Iterative Refined Speech Separation Based on Context-Aware Dual-Path Parallel Bi-LSTM
- Target Speaker Extraction for Overlapped Multi-Talker Speaker Verification