Video-Driven Speech Reconstruction using Generative Adversarial Networks
This addresses the challenge of communication breakdowns when audio is missing, offering a novel solution for applications like assistive technologies or video enhancement, though it is incremental as it builds on existing GAN-based methods.
The paper tackles the problem of reconstructing speech from silent video by developing an end-to-end temporal model using GANs that directly synthesizes raw audio, achieving natural-sounding and intelligible speech synchronized with video, with evaluation on the GRID dataset showing it works for both speaker-dependent and independent scenarios.
Speech is a means of communication which relies on both audio and visual information. The absence of one modality can often lead to confusion or misinterpretation of information. In this paper we present an end-to-end temporal model capable of directly synthesising audio from silent video, without needing to transform to-and-from intermediate features. Our proposed approach, based on GANs is capable of producing natural sounding, intelligible speech which is synchronised with the video. The performance of our model is evaluated on the GRID dataset for both speaker dependent and speaker independent scenarios. To the best of our knowledge this is the first method that maps video directly to raw audio and the first to produce intelligible speech when tested on previously unseen speakers. We evaluate the synthesised audio not only based on the sound quality but also on the accuracy of the spoken words.