| Paper: | SLP-P20.9 | ||
| Session: | Acoustic Modeling and Adaptation | ||
| Time: | Friday, May 19, 14:00 - 16:00 | ||
| Presentation: | Poster | ||
| Topic: | Speech and Spoken Language Processing: Speaker adaptation and normalization (e.g., VTLN) | ||
| Title: | ADAPTATION OF HYBRID ANN/HMM MODELS USING LINEAR HIDDEN TRANSFORMATIONS AND CONSERVATIVE TRAINING | ||
| Authors: | Roberto Gemello, Franco Mana, Loquendo, Italy; Stefano Scanzio, Pietro Laface, Politecnico di Torino, Italy; Renato De Mori, University of Avignon, France | ||
| Abstract: | 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. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012