- Recherche et sélection de publications
|
Deep-neural network approaches for speech recognition with heterogeneous groups of speakers including children
- Romain Serizel #1, Diego Giuliani
-
#1 |
Laboratoire Traitement et Communication de l'Information [Paris] (LTCI)
- Télécom ParisTech
- CNRS : UMR5141
|
- References
- Natural Language Engineering, April 2016,
- Abstract
This paper introduces deep neural network (DNN) - hidden Markov model (HMM) based methods to tackle speech recognition in heterogeneous groups of speakers including children. We target three speaker groups consisting of children, adult males and adult females. Two different kind of approaches are introduced here: approaches based on DNN adaptation and approaches relying on vocal-tract length normalisation (VTLN).
First, the recent approach that consists
in adapting a general DNN to domain/language specific data is extended to target age/gender groups in the context of DNN-HMM. Then, VTLN is investigated by training a DNN-HMM system by using either mel frequency cepstral coefficients (MFCC) normalised with standard VTLN or MFCC derived acoustic features combined with the posterior probabilities of the VTLN warping factors. In this later, novel, approach the posterior probabilities of the warping factors are obtained with a separate DNN and the decoding can be operated in a single pass when the VTLN approach requires two decoding passes. Finally, the different approaches presented here are combined to take advantage of their complementarity. The combination of several approaches is shown to improve the baseline phone error rate performance by 30% to 35% relative and the baseline word error rate performance by about 10% relative.
- Keywords
- automatic speech recognition, children’s speech recognition, deep neural networks
- Category
- Article in peer reviewed Journal
- Research Area(s)
- Engineering Sciences/Signal and Image processing
- Identifier(s)
-
Bibliographic key Serizel2015c
- File(s)
-
- Export
-
- Last update
- on may 25, 2016
|