Transformer-S2A: Robust and Efficient Speech-to-Animation
This work addresses the need for cross-language and cross-speaker facial animation in human-computer interaction, with incremental improvements in efficiency and robustness.
The paper tackles the problem of generating synchronized facial animation from speech by proposing a robust and efficient Speech-to-Animation approach, achieving a 17x inference speedup compared to state-of-the-art methods.
We propose a novel robust and efficient Speech-to-Animation (S2A) approach for synchronized facial animation generation in human-computer interaction. Compared with conventional approaches, the proposed approach utilizes phonetic posteriorgrams (PPGs) of spoken phonemes as input to ensure the cross-language and cross-speaker ability, and introduces corresponding prosody features (i.e. pitch and energy) to further enhance the expression of generated animation. Mixture-of-experts (MOE)-based Transformer is employed to better model contextual information while provide significant optimization on computation efficiency. Experiments demonstrate the effectiveness of the proposed approach on both objective and subjective evaluation with 17x inference speedup compared with the state-of-the-art approach.