Audio-visual speech recognition in vehicular noise using a multi-classifier approach

Karabalkan, Harun and Erdoğan, Hakan (2007) Audio-visual speech recognition in vehicular noise using a multi-classifier approach. In: Biennial on DSP for in-Vehicle and Mobile Systems, Istanbul, Turkey

[thumbnail of paper113_v04.pdf] PDF
paper113_v04.pdf

Download (144kB)

Abstract

Speech recognition accuracy can be increased and noise robustness can be improved by taking advantage of the visual speech information acquired from the lip region. To combine audio and visual information sources, efficient information fusion techniques are required. In this paper, we propose a novel SVM-HMM tandem hybrid feature extraction and combination method for an audio-visual speech recognition system. From each stream, multiple one-versus-rest support vector machine (SVM) binary classifiers are trained where each word is considered as a class in a limited vocabulary speech recognition scenario. The outputs of the binary classifiers are treated as a vector of features to be combined with the vector from the other stream and new combining binary classifiers are built. The outputs of the classifiers are used as observed features in hidden Markov models (HMM) representing words. The whole process can be considered as a nonlinear feature dimension reduction system which extracts highly discriminatory features from limited amounts of training data. To simulate the performance of the system in a real-world environment, we add vehicular noise at different SNRs to speech data and perform extensive experiments.
Item Type: Papers in Conference Proceedings
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Hakan Erdoğan
Date Deposited: 31 Oct 2007 20:43
Last Modified: 26 Apr 2022 08:44
URI: https://research.sabanciuniv.edu/id/eprint/6908

Actions (login required)

View Item
View Item