Recent advances in Automatic Speech Recognition for Vietnamese

Viet-Bac Le (1) , Laurent Besacier (2) , Sopheap Seng (2) , Brigitte Bigi (2) , Thi-Ngoc-Diep Do (2)

1 Vocapia Research [Orsay]
2 CLIPS - IMAG - Communication Langagière et Interaction Personne-Système

This paper presents our recent activities for automatic speech recognition for Vietnamese. First, our text data collection and processing methods and tools are described. For language modeling, we investigate word, sub-word and also hybrid word/sub-word models. For acoustic modeling, when only limited speech data are available for Vietnamese, we propose some crosslingual acoustic modeling techniques. Furthermore, since the use of sub-word units can reduce the high out-of-vocabulary rate and improve the lack of text resources in statistical language modeling, we propose several methods to decompose, normalize and combine word and sub-word lattices generated from different ASR systems. Experimental results evaluated on the VnSpeechCorpus demonstrate the feasibility of our methods.

Mots clés: language modeling; acoustic modeling; word; sub-word unit; Index Terms – ASR; Vietnamese

Domaines: Informatique et langage [cs.CL]; Sciences de l'information et de la communication

Viet-Bac Le, Laurent Besacier, Sopheap Seng, Brigitte Bigi, Thi-Ngoc-Diep Do. Recent advances in Automatic Speech Recognition for Vietnamese. The first International Workshop on Spoken Languages Technologies for Under-resourced languages, 2008, Hanoi, Vietnam. ⟨hal-01705670⟩