English

Towards Lipreading Sentences with Active Appearance Models

Image and Video Processing 2018-05-31 v1 Audio and Speech Processing

Abstract

Automatic lipreading has major potential impact for speech recognition, supplementing and complementing the acoustic modality. Most attempts at lipreading have been performed on small vocabulary tasks, due to a shortfall of appropriate audio-visual datasets. In this work we use the publicly available TCD-TIMIT database, designed for large vocabulary continuous audio-visual speech recognition. We compare the viseme recognition performance of the most widely used features for lipreading, Discrete Cosine Transform (DCT) and Active Appearance Models (AAM), in a traditional Hidden Markov Model (HMM) framework. We also exploit recent advances in AAM fitting. We found the DCT to outperform AAM by more than 6% for a viseme recognition task with 56 speakers. The overall accuracy of the DCT is quite low (32-34%). We conclude that a fundamental rethink of the modelling of visual features may be needed for this task.

Keywords

Cite

@article{arxiv.1805.11688,
  title  = {Towards Lipreading Sentences with Active Appearance Models},
  author = {George Sterpu and Naomi Harte},
  journal= {arXiv preprint arXiv:1805.11688},
  year   = {2018}
}

Comments

Presented at The 14th International Conference on Auditory-Visual Speech Processing (AVSP 2017)

R2 v1 2026-06-23T02:12:34.768Z