Deep Learning-based Automated Lip-Reading: A Survey
Journal article
Fenghour, S., Chen, D., Guo, K., Li, B. and Xiao, P. (2021). Deep Learning-based Automated Lip-Reading: A Survey. IEEE Access. https://doi.org/10.1109/ACCESS.2021.3107946
Authors | Fenghour, S., Chen, D., Guo, K., Li, B. and Xiao, P. |
---|---|
Abstract | A survey on automated lip-reading approaches is presented in this paper with the main focus being on deep learning related methodologies which have proven to be more fruitful for both feature extraction and classification. This survey also provides comparisons of all the different components that make up automated lip-reading systems including the audio-visual databases, feature extraction, classification networks and classification schemas. The main contributions and unique insights of this survey are: 1) A comparison of Convolutional Neural Networks with other neural network architectures for feature extraction; 2) A critical review on the advantages of Attention-Transformers and Temporal Convolutional Networks to Recurrent Neural Networks for classification; 3) A comparison of different classification schemas used for lip-reading including ASCII characters, phonemes and visemes, and 4) A review of the most up-to-date lip-reading systems up until early 2021. |
Keywords | Visual speech recognition; lip-reading; deep learning; feature extraction; classification; computer vision; natural language processing |
Year | 2021 |
Journal | IEEE Access |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ACCESS.2021.3107946 |
Publication dates | |
25 Aug 2021 | |
Publication process dates | |
Accepted | 08 Aug 2021 |
Deposited | 10 Aug 2021 |
Publisher's version | License File Access Level Open |
Accepted author manuscript | License File Access Level Controlled |
https://openresearch.lsbu.ac.uk/item/8x723
Download files
Publisher's version
Deep_Learning-Based_Automated_Lip-Reading_A_Survey.pdf | ||
License: CC BY 4.0 | ||
File access level: Open |
245
total views733
total downloads1
views this month4
downloads this month