Back to Search
Start Over
Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement
- Publication Year :
- 2021
-
Abstract
- As the cornerstone of other important technologies, such as speech recognition and speech synthesis, speech enhancement is a critical area in audio signal processing. In this paper, a new deep learning structure for speech enhancement is demonstrated. The model introduces a "full" attention mechanism to a bidirectional sequence-to-sequence method to make use of latent information after each focal frame. This is an extension of the previous attention-based RNN method. The proposed bidirectional attention-based architecture achieves better performance in terms of speech quality (PESQ), compared with OM-LSA, CNN-LSTM, T-GSA and the unidirectional attention-based LSTM baseline.<br />Comment: 4 pages
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2108.12105
- Document Type :
- Working Paper