Adaptation of Hybrid ANN/HMM Models Using Linear Hidden Transformations and Conservative Training - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Adaptation of Hybrid ANN/HMM Models Using Linear Hidden Transformations and Conservative Training

Roberto Gemello
  • Fonction : Auteur
  • PersonId : 982496
Franco Mana
  • Fonction : Auteur
Stefano Scanzio
  • Fonction : Auteur

Résumé

A technique is proposed for the adaptation of automatic speech recognition systems using Hybrid models combining Artificial Neural Networks with Hidden Markov Models. The application of linear transformations not only to the input features, but also to the outputs of the internal layers is investigated. The motivation is that the outputs of an internal layer represent a projection of the input pattern into a space where it should be easier to learn the classification or transformation expected at the output of the network. A new solution, called Conservative Training, is proposed that compensates for the lack of adaptation samples in certain classes. Supervised adaptation experiments with different corpora and for different adaptation types are described. The results show that the proposed approach always outperforms the use of transformations in the feature space and yields even better results when combined with linear input transformations.

Dates et versions

hal-01320124 , version 1 (23-05-2016)

Identifiants

Citer

Roberto Gemello, Franco Mana, Stefano Scanzio, Pietro Laface, Renato de Mori. Adaptation of Hybrid ANN/HMM Models Using Linear Hidden Transformations and Conservative Training. IEEE International Conference on Acoustics, Speech and Signal Processing, May 2006, Toulouse, France. ⟨10.1109/ICASSP.2006.1660239⟩. ⟨hal-01320124⟩

Collections

UNIV-AVIGNON LIA
68 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More