Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models
This work addresses the challenge of generating realistic lip animations from speech for applications like virtual avatars, though it is incremental as it builds on existing acoustic models.
The paper tackled the problem of speaker-independent speech-driven visual speech synthesis by adapting an automatic speech recognition acoustic model to the visual domain, resulting in animations that viewers significantly preferred over those from a randomly initialized model.
Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural networks (DNNs). However, a limitation is the lack of synchronized audio, video, and depth data required to reliably train the DNNs, especially for speaker-independent models. In this paper, we investigate adapting an automatic speech recognition (ASR) acoustic model (AM) for the visual speech synthesis problem. We train the AM on ten thousand hours of audio-only data. The AM is then adapted to the visual speech synthesis domain using ninety hours of synchronized audio-visual speech. Using a subjective assessment test, we compared the performance of the AM-initialized DNN to one with a random initialization. The results show that viewers significantly prefer animations generated from the AM-initialized DNN than the ones generated using the randomly initialized model. We conclude that visual speech synthesis can significantly benefit from the powerful representation of speech in the ASR acoustic models.