EUSIPCO'2002 banner

Paper data
Merging Segmental, Rhythmic and Fundamental Frequency Features for Automatic Language Identification

Rouas Jean-Luc, IRIT - UMR 5505 CNRS INPT UPS, France
Farinas Jérôme, IRIT - UMR 5505 CNRS INPT UPS, France
Pellegrino François, DDL - UMR 5596 CNRS Univ. Lyon 2, France

Page numbers in the proceedings:
Volume III pp 591-594

Language and Speech Recognition

Paper abstract
This paper deals with an approach to Automatic Language Identification based on rhythmic and fundamental frequency modeling. Experiments are performed on read speech for 5 European languages. They show that rhythm can be automatically extracted and is relevant in language identification: using cross-validation, 79% of correct identification is reached with 21 s. utterances. The fundamental frequency modeling, tested in the same conditions (cross-validation), produces 50% of correct identification for the 21 s. utterances. The Vowel System Modeling gives an identification rate of 70% for the 21 s. utterances. Last, merging the three models slightly improves the identification rate.

A PDF version is available here