2021/08/27 by Yuzi Yan, Wei-Qiang Zhang, Yan, Yuzi +3
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #cs.LG #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2108.12105
4 pages
arxiv created 2021/08/27 · openalex publication_date 2021/08/27 · arxiv updated 2021/08/30 · openalex created_date 2021/09/13 · openalex updated_date 2026/07/28
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.