Home

Contact

E-mail
Homepage
LinkedIn
Google citations


Research

Publication list
PhD Thesis(Eurasip PhD Library)

Deep neural network adaptation for children's and adults' speech recognition



Authors: Romain Serizel, Diego Giuliani

Reference: in Proc of the first Italian Computational Linguistics Conference (CLiC-it), Pisa, Italy, Dec. 2014.

Status: Published (International Conference)

Abstract:
This paper introduces a novel application of the hybrid deep neural network (DNN) - hidden Markov model (HMM) approach for automatic speech recognition (ASR) to target groups of speakers of a specific age/gender. The group-specific training of DNN is investigated and shown to be inefficient when the amount of training data is limited. To overcome this problem, 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 hybrid DNN-HMM systems, reducing consistently the phone error rate by 15-20\% relative for the three different speaker groups.

PDF File
BibTeX


This page is maintained by Romain Serizel.
Last modification: