Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition

Résumé

This paper introduces approaches based on vocal tract length normalisation (VTLN) techniques for hybrid deep neural network (DNN)-hidden Markov model (HMM) automatic speech recognition when targeting children's and adults' speech. VTLN is investigated by training a DNN-HMM system by using first mel frequency cepstral coefficients (MFCCs) normalised with standard VTLN. Then, MFCCs derived acoustic features are combined with the VTLN warping factors to obtain an augmented set of features as input to a DNN. In this later, novel, approach 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. Both VTLN-based approaches are shown to improve phone error rate performance, up to 20% relative improvement, compared to a baseline trained on a mixture of children's and adults' speech.
Fichier principal
Vignette du fichier
14-3.pdf (61.1 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01393972 , version 1 (09-11-2016)

Identifiants

Citer

Romain Serizel, Diego Giuliani. Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition. 2014 IEEE Spoken Language Technology Workshop (SLT 2014), Dec 2014, South Lake Tahoe, CA, United States. pp.135-140, ⟨10.1109/SLT.2014.7078563⟩. ⟨hal-01393972⟩
140 Consultations
841 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More