Skip to Main content Skip to Navigation
Journal articles

Deep-neural network approaches for speech recognition with heterogeneous groups of speakers including children

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 kinds 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 standard VTLN approach requires two decoding passes. Finally, the different approaches presented here are combined to take advantage of their complementarity. System combination approaches are 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.
Complete list of metadata

Cited literature [54 references]  Display  Hide  Download

https://hal.inria.fr/hal-01390905
Contributor : Romain Serizel <>
Submitted on : Tuesday, November 8, 2016 - 1:28:55 PM
Last modification on : Wednesday, May 19, 2021 - 4:52:03 PM
Long-term archiving on: : Tuesday, March 14, 2017 - 10:24:25 PM

File

15-1.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01390905, version 1

Collections

Citation

Romain Serizel, Diego Giuliani. Deep-neural network approaches for speech recognition with heterogeneous groups of speakers including children. Natural Language Engineering, Cambridge University Press (CUP), 2016, 1, pp.0 - 0. ⟨hal-01390905⟩

Share

Metrics

Record views

323

Files downloads

639