Learning Audio-Visual Dereverberation

Changan Chen, Wei Sun, David Harwath, Kristen Grauman

Keywords: speech enhancement, audio-visual learning, speech dereverberation, room acoustics

Abstract: Reverberation from audio reflecting off surfaces and objects in the environment not only degrades the quality of speech for human perception, but also severely impacts the accuracy of automatic speech recognition. Prior work attempts to remove reverberation based on the audio modality only. Our idea is to learn to dereverberate speech from audio-visual observations. The visual environment surrounding a human speaker reveals important cues about the room geometry, materials, and speaker location, all of which influence the precise reverberation effects in the audio stream. We introduce Visually-Informed Dereverberation of Audio (VIDA), an end-to-end approach that learns to remove reverberation based on both the observed sounds and visual scene. In support of this new task, we develop a large-scale dataset that uses realistic acoustic renderings of speech in real-world 3D scans of homes offering a variety of room acoustics. Demonstrating our approach on both simulated and real imagery for speech enhancement, speech recognition, and speaker identification, we show it achieves state-of-the-art performance and substantially improves over traditional audio-only methods.

One-sentence Summary: We propose to dereverberate speech by leveraging the visual stream, which reveals cues about room geometry, materials, and speaker locations.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2106.07732/code)