next up previous contents
Next: Task 5.2: Global Discrimination Up: Task 5.1: Perceptual Models Previous: Combining multiple time-scale features

Task 5.1: Future Developments

It appears that sub-band alignments can have significant timing deviations from the full-band alignments; thus, we would expect that there is a potential for improvements in acoustic modeling if longer time-scale information stream merging (i.e., phone or syllable) is used.

Preliminary work on multiple stream recognition will now be extended in several directions, including:

Christophe Ris