A boosted multi-HMM classifier for recognition of visual speech elements

• Main Authors: Foo, Say Wei, Dong, Liang
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2009
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/90750; http://hdl.handle.net/10220/4590; http://sfxna09.hosted.exlibrisgroup.com:3410/ntu/sfxlcl3?sid=metalib:PUBMED&id=doi:10.1080/02699200400026884&genre=&isbn=&issn=0269-9206&date=&volume=20&issue=2-3&spage=149&epage=56&aulast=Parker&aufirst=%20Mark&auinit=&title=Clin%20Linguist%20Phon&atitle=Automatic%20speech%20recognition%20and%20training%20for%20severely%20dysarthric%20users%20of%20assistive%20technology%3A%20the%20STARDUST%20project%2E
• Institution: Nanyang Technological University

A novel boosted classifier using multiple Hidden Markov Models (HMMs) is reported in this paper. The composite HMMs are specially trained to highlight certain group of training samples with the application of adaptive boosting technique. Experiments were carried out to identify the ba...