2023/07/23 by Yoshiki Masuyama, Masuyama, Yoshiki, Xuankai Chang +13
Computer Science · Neuroscience · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Hearing Loss and Rehabilitation #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2307.12231
openalex publication_date 2023/07/23 · openalex created_date 2023/07/26 · openalex updated_date 2026/07/28
Neural speech separation has made remarkable progress and its integration with automatic speech recognition (ASR) is an important direction towards realizing multi-speaker ASR. This work provides an insightful investigation of speech separation in reverberant and noisy-reverberant scenarios as an ASR front-end. In detail, we explore multi-channel separation methods, mask-based beamforming and complex spectral mapping, as well as the best features to use in the ASR back-end model. We employ the recent self-supervised learning representation (SSLR) as a feature and improve the recognition performance from the case with filterbank features. To further improve multi-speaker recognition performance, we present a carefully designed training strategy for integrating speech separation and recognition with SSLR. The proposed integration using TF-GridNet-based complex spectral mapping and WavLM-based SSLR achieves a 2.5% word error rate in reverberant WHAMR! test set, significantly outperforming an existing mask-based MVDR beamforming and filterbank integration (28.9%).