Bimodal recognition experiments with recurrent neural networks
- 17 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. ii, II/553-II/556
- https://doi.org/10.1109/icassp.1994.389596
Abstract
A bimodal automatic speech recognition system, using simultaneously auditory model and articulatory parameters, is described. Results given for various speaker dependent phonetic recognition experiments, regarding the Italian plosive class, show the usefulness of this approach especially in noisy conditions.Keywords
This publication has 9 references indexed in Scilit:
- 3d Movement Detecticn: A Hierarchical ApproachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Neural network lipreading system for improved speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Articulatory dynamics of lips in Italian /'vpv/ and /'vbv/ sequencesPublished by International Speech Communication Association ,1993
- SLAM: segmentation and labelling automatic modulePublished by International Speech Communication Association ,1993
- Phonetic recognition experiments with recurrent neural networksPublished by International Speech Communication Association ,1992
- BPS: a learning algorithm for capturing the dynamic nature of speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- A joint synchrony/mean-rate model of auditory speech processingJournal of Phonetics, 1988
- Quantifying the contribution of vision to speech perception in noiseBritish Journal of Audiology, 1987
- Elite: A Digital Dedicated Hardware System for Movement Analysis Via Real-Time TV Signal ProcessingIEEE Transactions on Biomedical Engineering, 1985