Reconnaissance de la parole continue à grand vocabulaire en vietnamien, une langue syllabique tonale

Hong-Quang Nguyen (1, 2) , Pascal Nocera (1) , Eric Castelli (2) , van Loan Trinh (2)

1 LIA - Laboratoire Informatique d'Avignon
2 MICA - International Research Institute MICA

This paper proposes a method to build a Vietna-mese Large Vocabulary Continuous Speech Recognition system (Vietnamese LVCSR system). The difference between Vietnamese and European languages is analyzed and used to adapt a LVCSR system for European languages to Vietnamese. Experiments are implemented on the VNSPEECHCORPUS. The results show that the accuracy of Vietnamese recognition system is increased by using Vietnamese language characteristics.

Mots clés: Automatic speech recognition; Vietna-mese language; minority language; tone recognition; compound noun

Domaines: Informatique [cs]

Hong-Quang Nguyen, Pascal Nocera, Eric Castelli, van Loan Trinh. Reconnaissance de la parole continue à grand vocabulaire en vietnamien, une langue syllabique tonale. Les Journées d’Etude sur la Parole (JEP), Jun 2008, Avignon, France. ⟨hal-01314293⟩