Abstract:
In this paper an in depth analysis is undertaken into effective strategies for integrating the audiovisual modalities for the purposes of text-dependent speaker recognition. Our work is based around the well known hidden Markov model (HMM) classifier framework for modelling speech. A framework is proposed to handle the mismatch between train and test observation sets, so as to provide effective classifier combination performance between the acoustic and visual HMM classifiers. From this framework, it can be shown that strategies for combining independent classifiers, such as the weighted product or sum rules, naturally emerge depending on the influence of the mismatch. Based on the assumption that poor performance in most audiovisual speaker recognition applications can be attributed to train/test mismatches we propose that the main impetus of practical audiovisual integration is to dampen the independent errors, resulting from the mismatch, rather than trying to model any bimodal speech dependencies. To this end a strategy is recommended , based on theory and empirical evidence, using a hybrid between the weighted product and weighted sum rules in the presence of varying acoustic noise. Results are presented on the M2VTS database.
