Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Vietnamese Large Vocabulary Continuous Speech Recognition

Thang Tat Vu (1), Dung Tien Nguyen (2), Mai Chi Luong (2), John-Paul Hosom (3)

(1) JAIST, Japan; (2) Vietnamese Academy of Science & Technology, Vietnam; (3) Oregon Health & Science University, USA

This paper presents an early study on building Vietnamese large vocabulary continuous speech recognition with concentration on choosing type of units and feature set. Our experiments were done using the HTK Toolkit and VOV broadcast corpus. The results show that the recognizer with mixture units achieved better performance than recognizers with initial-final units and phoneme units. Among feature sets are applied, MFCC has performance somewhat better than PLP, and the combination of MFCC and F0 features increases the accuracy of the Vietnamese recognition system.

Full Paper

Bibliographic reference.  Vu, Thang Tat / Nguyen, Dung Tien / Luong, Mai Chi / Hosom, John-Paul (2005): "Vietnamese large vocabulary continuous speech recognition", In INTERSPEECH-2005, 1689-1692.