Output details
11 - Computer Science and Informatics
London Metropolitan University
Audio-visual fuzzy fusion for robust
speech recognition
<24> This research undertakes one of the hottest topics in speech signal processing, particularly when applied within a noisy environment. It proposes a fuzzy logic-based data fusion method that combines the capabilities of two working schemes, namely the automatic speech recognition system and the automatic visual recognition system. This approach provides a powerful method that enables simpler data fusion at decision level, rather than the more complex at data and features level. The findings helped to establish a framework for the development of bimodal speech recognition and speaker’s identification system using a fuzzy logic fusion methodology.