Viseme Embeddings For Commonly Confused Words In Lip-Reading
Conference paper
Fenghour, S., Chen, D., Guo, K. and Xiao, P. (2022). Viseme Embeddings For Commonly Confused Words In Lip-Reading. 7th International Conference on Big Data Analytics, Data Mining and Computational Intelligence. Lisbon 20 - 22 Jul 2022
Authors | Fenghour, S., Chen, D., Guo, K. and Xiao, P. |
---|---|
Type | Conference paper |
Abstract | Automating lip reading has attracted a lot of research attention in the last several years and there exists a wide variety of applications where automated lip reading could be implemented, including forensic CCTV footage or to assist those with language impairment. Obstacles for both professional lip-readers and automated lipreading systems is not only the situation of different-sounding words being confused because they produce identical lip movements, but also that word with similar lip movements can easily be confused because they have sequences of visemes that are similar. This paper proposes a library and corpus called Visemes2Vec for learning the embeddings of viseme sequences as a contribution and is to the best of our knowledge the first attempt at proposing library for visualising words that have similar lip movements. Visemes2Vec is analogous to Word2Vec which groups together that are semantically similar in meaning or Chars2Vec which groups together words that share common characters. |
Keywords | Lip-Reading; Speech Recognition; Visemes; Embeddings; Neural Networks; Principal Component Analysis |
Year | 2022 |
Web address (URL) | https://bigdaci.org/ |
Accepted author manuscript | License File Access Level Open |
Publication dates | |
20 Jul 2022 | |
Publication process dates | |
Accepted | 10 Jun 2022 |
Deposited | 30 Jun 2022 |
https://openresearch.lsbu.ac.uk/item/913w0
Download files
Accepted author manuscript
2022 05 17 VISEME EMBEDDINGS FOR COMMONLY CONFUSED WORDS IN LIP-READING.doc | ||
License: CC BY 4.0 | ||
File access level: Open |
20
total views3
total downloads6
views this month1
downloads this month