Real-Time System for Audio-Visual Target Speech Enhancement
This work addresses the problem of robust speech enhancement in noisy environments for users needing real-time applications, but it is incremental as it builds on prior audio-visual methods by focusing on CPU-based implementation.
The authors tackled real-time audio-visual speech enhancement by developing RAVEN, a system that runs on CPU hardware and uses visual cues like lip movements to extract clean speech from noise, interfering speakers, and other sounds, enabling live demonstrations with microphone and webcam setups.
We present a live demonstration for RAVEN, a real-time audio-visual speech enhancement system designed to run entirely on a CPU. In single-channel, audio-only settings, speech enhancement is traditionally approached as the task of extracting clean speech from environmental noise. More recent work has explored the use of visual cues, such as lip movements, to improve robustness, particularly in the presence of interfering speakers. However, to our knowledge, no prior work has demonstrated an interactive system for real-time audio-visual speech enhancement operating on CPU hardware. RAVEN fills this gap by using pretrained visual embeddings from an audio-visual speech recognition model to encode lip movement information. The system generalizes across environmental noise, interfering speakers, transient sounds, and even singing voices. In this demonstration, attendees will be able to experience live audio-visual target speech enhancement using a microphone and webcam setup, with clean speech playback through headphones.