Contextual Hidden Markov Models

Mathieu Radenen 1 Thierry Artières 1
1 MALIRE - Machine Learning and Information Retrieval
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Multiple works have proposed extensions of HMMs for handling variability. We focus here on the design of HMMs whose probability distribution on sequences depends on additional external variables that we call the context, which may stand for emotion features in speech recognition, physical features in gesture recognition, etc. We show experimentally the relevance of the method for handwriting recognition.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustics, Speech, and Signal Processing, Mar 2012, Kyoto, Japan. IEEE, IEEE International Conference on Acoustics, Speech, and Signal Processing, pp.2113-2116, 〈10.1109/ICASSP.2012.6288328〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01273312
Contributeur : Lip6 Publications <>
Soumis le : vendredi 12 février 2016 - 11:40:10
Dernière modification le : mercredi 21 mars 2018 - 18:58:10

Identifiants

Collections

Citation

Mathieu Radenen, Thierry Artières. Contextual Hidden Markov Models. IEEE International Conference on Acoustics, Speech, and Signal Processing, Mar 2012, Kyoto, Japan. IEEE, IEEE International Conference on Acoustics, Speech, and Signal Processing, pp.2113-2116, 〈10.1109/ICASSP.2012.6288328〉. 〈hal-01273312〉

Partager

Métriques

Consultations de la notice

184