2022/05/20 by Meng Yu, Yong Xu, Yu, Meng +7
Computer Science · Engineering · Neuroscience · #Advanced Adaptive Filtering Techniques #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Hearing Loss and Rehabilitation #Sound (cs.SD) #Speech and Audio Processing #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2205.10401
Submitted to INTERSPEECH 2022
arxiv created 2022/05/20 · openalex publication_date 2022/05/20 · arxiv updated 2022/05/24 · openalex created_date 2022/05/26 · openalex updated_date 2026/07/28
Acoustic echo cancellation (AEC) plays an important role in the full-duplex speech communication as well as the front-end speech enhancement for recognition in the conditions when the loudspeaker plays back. In this paper, we present an all-deep-learning framework that implicitly estimates the second order statistics of echo/noise and target speech, and jointly solves echo and noise suppression through an attention based recurrent neural network. The proposed model outperforms the state-of-the-art joint echo cancellation and speech enhancement method F-T-LSTM in terms of objective speech quality metrics, speech recognition accuracy and model complexity. We show that this model can work with speaker embedding for better target speech enhancement and furthermore develop a branch for automatic gain control (AGC) task to form an all-in-one front-end speech enhancement system.