Improving Speech Recognition through Automatic Selection of Age Group Specific Acoustic Models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Improving Speech Recognition through Automatic Selection of Age Group Specific Acoustic Models

Résumé

The acoustic models used by automatic speech recognisers are usually trained with speech collected from young to middle-aged adults. As the characteristics of speech change with age, such acoustic models tend to perform poorly on children's and elderly people's speech. In this study, we investigate whether the automatic age group classification of speakers, together with age group -specific acoustic models, could improve automatic speech recognition performance. We train an age group classifier with an accuracy of about 95% and show that using the results of the classifier to select age group -specific acoustic models for children and the elderly leads to considerable gains in automatic speech recognition performance, as compared with using acoustic models trained with young to middle-aged adults' speech for recognising their speech, as well.
Fichier principal
Vignette du fichier
Hamalainen_13046.pdf (441.97 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01146743 , version 1 (29-04-2015)

Identifiants

  • HAL Id : hal-01146743 , version 1
  • OATAO : 13046

Citer

Annika Hämäläinen, Hugo Meinedo, Michael Tjalve, Thomas Pellegrini, Isabel Trancoso, et al.. Improving Speech Recognition through Automatic Selection of Age Group Specific Acoustic Models. International Conference on Computational Processing of Portuguese - PROPOR 2014, Oct 2014, São Carlos, Brazil. pp. 12-23. ⟨hal-01146743⟩
115 Consultations
401 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More