Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection
This work addresses the challenge of accurate speech recognition in noisy environments with multiple speakers, though it is incremental as it builds on prior multi-task approaches.
The paper tackles the problem of improving automatic speech recognition (ASR) in noisy, multi-speaker video settings by jointly training a model for ASR and active speaker detection (ASD), reducing ASD classification error by approximately 25% while enhancing ASR performance compared to a baseline.
Under noisy conditions, automatic speech recognition (ASR) can greatly benefit from the addition of visual signals coming from a video of the speaker's face. However, when multiple candidate speakers are visible this traditionally requires solving a separate problem, namely active speaker detection (ASD), which entails selecting at each moment in time which of the visible faces corresponds to the audio. Recent work has shown that we can solve both problems simultaneously by employing an attention mechanism over the competing video tracks of the speakers' faces, at the cost of sacrificing some accuracy on active speaker detection. This work closes this gap in active speaker detection accuracy by presenting a single model that can be jointly trained with a multi-task loss. By combining the two tasks during training we reduce the ASD classification accuracy by approximately 25%, while simultaneously improving the ASR performance when compared to the multi-person baseline trained exclusively for ASR.