Portuguese Variety Identification on Broadcast News

Jean-Luc Rouas (1, 2, 3, 4) , Isabel Trancoso (5) , Céu Viana (6) , Mónica Abreu (5)

1 L2F - Laboratorio de Sistemas de Lingua Falada
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique
3 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
4 INRETS/LEOST - Laboratoire Electronique, Ondes et Signaux pour les Transports
5 L2F - Spoken Language Systems Laboratory [Portugal]
6 CLUL - Centro de Linguística da Universidade de Lisboa

This paper describes an accent identification system for Portuguese, that explores different type of properties: acoustic, phonotactic and prosodic. The system is designed to be used as a pre-processing module for the Portuguese Automatic Speech Recognition system developed at INESC-ID. In terms of variety identification, the overall rate of correct identification is 69.0% if all 7 varieties are considered, and the best results are obtained for Brazilian Portuguese, also the variety that proved easiest to identify in perceptual experiments. When distinguishing between European, Brazilian and African Portuguese, the identification rate goes up to 94.7%. The fact that the prosodic system alone can achieve an identification rate of 77% is also worth investigating.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Jean-Luc Rouas, Isabel Trancoso, Céu Viana, Mónica Abreu. Portuguese Variety Identification on Broadcast News. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), Mar 2008, Las Vegas, United States. pp.4229-4232. ⟨hal-00664984⟩