In this paper, we introduce a new approach for multi-band speech recognition which allows interaction between sub-bands and does not require a recombination step. Moreover, this approach is a natural generalization of the HMMs paradigm and leads to fast learning and recognition algorithms.
Cite as: Daoudi, K., Fohr, D., Antoine, C. (2000) A new approach for multi-band speech recognition based on probabilistic graphical models. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 1, 329-332, doi: 10.21437/ICSLP.2000-82
@inproceedings{daoudi00_icslp, author={Khalid Daoudi and Dominique Fohr and Christophe Antoine}, title={{A new approach for multi-band speech recognition based on probabilistic graphical models}}, year=2000, booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)}, pages={vol. 1, 329-332}, doi={10.21437/ICSLP.2000-82} }