English

Visual-speech Synthesis of Exaggerated Corrective Feedback

Audio and Speech Processing 2020-12-16 v2 Artificial Intelligence

Abstract

To provide more discriminative feedback for the second language (L2) learners to better identify their mispronunciation, we propose a method for exaggerated visual-speech feedback in computer-assisted pronunciation training (CAPT). The speech exaggeration is realized by an emphatic speech generation neural network based on Tacotron, while the visual exaggeration is accomplished by ADC Viseme Blending, namely increasing Amplitude of movement, extending the phone's Duration and enhancing the color Contrast. User studies show that exaggerated feedback outperforms non-exaggerated version on helping learners with pronunciation identification and pronunciation improvement.

Keywords

Cite

@article{arxiv.2009.05748,
  title  = {Visual-speech Synthesis of Exaggerated Corrective Feedback},
  author = {Yaohua Bu and Weijun Li and Tianyi Ma and Shengqi Chen and Jia Jia and Kun Li and Xiaobo Lu},
  journal= {arXiv preprint arXiv:2009.05748},
  year   = {2020}
}
R2 v1 2026-06-23T18:29:20.713Z