Skip to Main content Skip to Navigation
Master Thesis

Amélioration des systèmes de reconnaissance de la parole des personnes âgées

Abstract : Recognition Automatic Speech is a burgeoning technology whose use for assistance to frail appears as an innovative area and hope. This dissertation was made in this context with the aim of assessing the state of the system for speech recognition to elderly in the CIRDO project. We studied from previous works on the subject, the differences between the non-elderly speaking and elderly speaking ; behavior of the system, after adjustments, thoroughly in terms of phonemes and classes of phonemes ; words decoding of speech for elderly with the WER metric. This research helped us better understand how the system works and finding a Sphinx3 parameterization which allows to obtain interesting results on a corpus of read speech voice aged and spontaneous speech, topic on which only very few studies exist.
Document type :
Master Thesis
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download
Contributor : UGA - LLASIC Sciences du langage & FLES Connect in order to contact the contributor
Submitted on : Friday, September 28, 2012 - 12:36:34 PM
Last modification on : Sunday, June 26, 2022 - 4:57:26 AM
Long-term archiving on: : Friday, December 16, 2016 - 6:34:48 PM


  • HAL Id : dumas-00736504, version 1


Juline Le Grand. Amélioration des systèmes de reconnaissance de la parole des personnes âgées. Sciences de l'Homme et Société. 2012. ⟨dumas-00736504⟩



Record views


Files downloads