Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network
This addresses the problem of distorted target speech in real listening environments for applications like hearing aids or communication systems, representing a strong incremental advance.
The paper tackles joint speech separation and dereverberation in noisy environments by proposing a two-stage multimodal network using audio and visual signals, achieving a 21.10% improvement in ESTOI and a 0.79 improvement in PESQ over unprocessed mixtures.
Background noise, interfering speech and room reverberation frequently distort target speech in real listening environments. In this study, we address joint speech separation and dereverberation, which aims to separate target speech from background noise, interfering speech and room reverberation. In order to tackle this fundamentally difficult problem, we propose a novel multimodal network that exploits both audio and visual signals. The proposed network architecture adopts a two-stage strategy, where a separation module is employed to attenuate background noise and interfering speech in the first stage and a dereverberation module to suppress room reverberation in the second stage. The two modules are first trained separately, and then integrated for joint training, which is based on a new multi-objective loss function. Our experimental results show that the proposed multimodal network yields consistently better objective intelligibility and perceptual quality than several one-stage and two-stage baselines. We find that our network achieves a 21.10% improvement in ESTOI and a 0.79 improvement in PESQ over the unprocessed mixtures. Moreover, our network architecture does not require the knowledge of the number of speakers.