Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
This work addresses the challenge of improving speech recognition and translation accuracy in noisy environments for users of AVSR systems, offering a versatile, unified model that is incremental but with strong performance gains.
The paper tackled the problem of limited video training data in Audio-Visual Speech Recognition (AVSR) by adapting the Whisper model to handle video inputs using gated cross attention, achieving state-of-the-art word error rates (e.g., 0.68% ASR and 0.76% AVSR on LRS3) and outperforming audio-only Whisper in noisy conditions for recognition and translation tasks.
Audio-Visual Speech Recognition (AVSR) uses lip-based video to improve performance in noise. Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours. In contrast, speech models such as Whisper are trained with hundreds of thousands of hours of data, and thus learn a better speech-to-text decoder. The huge training data difference motivates us to adapt Whisper to handle video inputs. Inspired by Flamingo which injects visual features into language models, we propose Whisper-Flamingo which integrates visual features into the Whisper speech recognition and translation model with gated cross attention. Our models achieve state-of-the-art ASR WER (0.68%) and AVSR WER (0.76%) on LRS3, and state-of-the-art ASR WER (1.3%) and AVSR WER (1.4%) on LRS2. Audio-visual Whisper-Flamingo outperforms audio-only Whisper on English speech recognition and En-X translation for 6 languages in noisy conditions. Moreover, Whisper-Flamingo is versatile and conducts all of these tasks using one set of parameters, while prior methods are trained separately on each language.