Single Channel Speech Enhancement Algorithm based on BLSTM-DNN Bidirectional Optimized Hybrid Model
Xiaoyue Sun, Ruwei Li, Tao Li, Dengcai Yang · IOP Conference Series Materials Science and Engineering · 2020
Abstract The performance of existing speech enhancement algorithms based on deep learning is not ideal in complex noise environment. To improve the problem, a bidirectional optimized hybrid network named BLSTM-DNN is constructed based on bidirectional long-short term memory (BLSTM) network and fully-connected deep neural network (DNN). This structure uses BLSTM to extract high-level information including past and future temporal context of noisy speech. Next, fully-connected DNN fits the high-level information to ideal ratio mask (IRM). Finally, the IRMs estimated by the BLSTM-DNN are used to enhance the noisy speech. Experimental results show that the proposed method can effectively improve the speech quality and intelligibility under unknown noise conditions.