TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain
arXiv:2103.09963
Abstract
In this paper, we propose a transformer-based architecture, called two-stage transformer neural network (TSTNN) for end-to-end speech denoising in the time domain. The proposed model is composed of an encoder, a two-stage transformer module (TSTM), a masking module and a decoder. The encoder maps input noisy speech into feature representation. The TSTM exploits four stacked two-stage transformer blocks to efficiently extract local and global information from the encoder output stage by stage. The masking module creates a mask which will be multiplied with the encoder output. Finally, the decoder uses the masked encoder feature to reconstruct the enhanced speech. Experimental results on the benchmark dataset show that the TSTNN outperforms most state-of-the-art models in time or frequency domain while having significantly lower model complexity.
arXiv comment5 pages, 4 figures, accepted by IEEE ICASSP 2021
References in corpus (4)
- MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement
- Phase-aware Speech Enhancement with Deep Complex U-Net
- Improved Speech Enhancement with the Wave-U-Net
- Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation