Novel Hybrid NN/HMM Modelling Techniques for On-line Handwriting Recognition

Abstract : In this work we propose two hybrid NN/HMM systems for handwriting recognition. The tied posterior model approximates the output probability density function of a Hidden Markov Model (HMM) with a neural net (NN). This allows a discriminative training of the model. The second system is the tandem approach: A NN is used as part of the feature extraction, and then a standard HMM apporach is applied. This adds more discrimination to the features. In an experimental section we compare the two proposed models with a baseline standard HMM system. We show that enhancing the feature vector has only a limited effect on the standard HMMs, but a significant influence to the hybrid systems. With an enhanced feature vector the two hybrid models highly outperform all baseline models. The tandem approach improves the recognition performance by 4.6% (52.9% rel. error reduction) absolute compared to the best baseline HMM.
Type de document :
Communication dans un congrès
Guy Lorette. Tenth International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule (France), Suvisoft, 2006
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00104794
Contributeur : Anne Jaigu <>
Soumis le : lundi 9 octobre 2006 - 14:24:04
Dernière modification le : lundi 9 octobre 2006 - 14:34:57
Document(s) archivé(s) le : mardi 6 avril 2010 - 19:01:53

Identifiants

  • HAL Id : inria-00104794, version 1

Collections

Citation

Joachim Schenk, Gerhard Rigoll. Novel Hybrid NN/HMM Modelling Techniques for On-line Handwriting Recognition. Guy Lorette. Tenth International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule (France), Suvisoft, 2006. 〈inria-00104794〉

Partager

Métriques

Consultations de la notice

287

Téléchargements de fichiers

514