Digital Signal Processing Reference
In-Depth Information
performances of individual likelihood sequences under acoustically clean
conditions.
6.
CONCLUSIONS
We have presented a multimodal (audio-lip-face) speaker identification
system that improves the identification performance over unimodal schemes.
These three independent sources of information with different reliabilities are
put together to propose a reliability ordering based multilevel decision
fusion. We observed significant improvement with WTAll decision fusion,
and a further improvement is achieved using the multilevel Bayesian
decision fusion. The reliability ordering is fixed with respect to the EER
performances of individual likelihood sequences under acoustically clean
conditions. However we should note that this reliability ordering is not
optimal under varying environmental conditions. Hence a better alternative is
to adaptively predict the reliability of each modality, so that an optimal
reliability ordering can be achieved for multilevel Bayesian decision fusion.
