Visual Speech Synthesis using Dynamic Visemes and Deep Learning Architectures

Thangthai, Ausdang (2018) Visual Speech Synthesis using Dynamic Visemes and Deep Learning Architectures. Doctoral thesis, University of East Anglia.

[thumbnail of 2018ThangthaiAPhD.pdf]
Download (45MB) | Preview


The aim of this work is to improve the naturalness of visual speech synthesis produced automatically from a linguistic input over existing methods. Firstly, the most important contribution is on the investigation of the most suitable speech units for the visual speech synthesis. We propose the use of dynamic visemes instead of phonemes or static visemes and found that dynamic visemes can generate better visual speech than either phone or static viseme units. Moreover, best performance is obtained by a combined phoneme-dynamic viseme system. Secondly, we examine the most appropriate model between hidden Markov model (HMM) and different deep learning models that include feedforward and recurrent structures consisting of one-to-one, many-to-one and many-to-many architectures. Results suggested that that frame-by-frame synthesis from deep learning approach outperforms state-based synthesis from HMM approaches and an encoder-decoder many-to-many architecture is better than the one-to-one and many-to-one architectures. Thirdly, we explore the importance of contextual features that include information at varying linguistic levels, from frame level up to the utterance level. Our findings found that frame level information is the most valuable feature, as it is able to avoid discontinuities in the visual feature sequence and produces a smooth and realistic animation output.
Fourthly, we found that the two most common objective measures of correlation and root mean square error are not able to indicate realism and naturalness of human perceived quality. We introduce an alternative objective measure and show that the global variance is a better indicator of human perception of quality. Finally, we propose a novel method to convert a given text input and phoneme transcription into a dynamic viseme transcription in the case when a reference dynamic viseme sequence is not available. Subjective preference tests confirmed that our proposed method is able to produce animation, that are statistically indistinguishable from animation produced using reference data.

Item Type: Thesis (Doctoral)
Faculty \ School: Faculty of Science > School of Computing Sciences
Depositing User: Megan Ruddock
Date Deposited: 19 Dec 2018 13:24
Last Modified: 19 Dec 2021 01:38

Actions (login required)

View Item View Item