The RACAD speech corpus of New Brunswick Acadian French: Design and applications

Authors

  • Wladyslaw Cichocki Department of French, University of New Brunswick, Fredericton, NB E3B 5A3, Canada
  • Sid-Ahmed Selouani Laboratoire LARIHS, Université de Moncton, Shippagan, NB E8S 1P6, Canada
  • Louise Beaulieu Secteur Arts et Sciences Humaines, Université de Moncton, Shippagan, NB E8S 1P6, Canada

Keywords:

Applications, Audio systems, Linguistics, Automatic speech recognition, Geographical locations, High-quality audio, Linguistic analysis, Recognition models, Recognition systems, Speech corpora, Word recognition

Abstract

The RACAD (Reconnaissance automatique de l'acadien) speech corpus contains high quality audio recordings that can be used to develop recognition systems for the regional varieties of French spoken in the province of New Brunswick, Canada. Its design is informed by linguistic analyses of Acadian French. The corpus contains sentences read by 140 speakers who were selected according to age, gender and geographical region. This paper presents a preliminary application of the corpus in automatic speech recognition research; it outlines an original global monophone recognition model that is designed to handle linguistic variability. Global phone and word recognition rates for this model are satisfactory (about 90%), but they vary considerably across geographical locations. Possible applications of the RACAD corpus in acoustic phonetic and socio-phonetic studies of dialect variation are also described in this paper.

Published

2008-12-01

How to Cite

1.
Cichocki W, Selouani S-A, Beaulieu L. The RACAD speech corpus of New Brunswick Acadian French: Design and applications. Canadian Acoustics [Internet]. 2008Dec.1 [cited 2021Jun.17];36(4):3-10. Available from: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/2098

Issue

Section

Technical Articles