# Video-Driven Speech Reconstruction using Generative Adversarial Networks

## TL;DR

This paper introduces an end-to-end GAN-based model that synthesizes natural, synchronized speech directly from silent video, achieving high intelligibility and sound quality even for unseen speakers.

## Contribution

It is the first to directly map silent video to raw audio and produce intelligible speech for previously unseen speakers.

## Key findings

- Produces natural, synchronized speech from silent video.
- Achieves high intelligibility and sound quality.
- Effective on both speaker-dependent and independent scenarios.

## Abstract

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.