SLTU-2008 - First International Workshop on Spoken Languages Technologies for Under-Resourced Languages

Hanoi, Vietnam
May 5-7, 2008

An Empirical Study of Multipass Decoding for Vietnamese LVCSR

Khoa Trinh, Ha Nguyen, Duc Duong, Quan Vu

Faculty of Information Technology, University of Science at VNU-HCM, HoChiMinh city, Vietnam

In this paper, we represent an empirical study of multipass decoding for Vietnamese LVCSR. We report our experiments with N-best, lattice and consensus decoding on the VNBN data. Results from this study indicate that our acoustic model for Vietnamese was precise. The results could be investigated in further steps to improve the performance of our system.

Index Terms Vietnamese, Acoustic Model, Language Model, N-best, Word Lattice, Confusion Network.

Full Paper

Bibliographic reference.  Trinh, Khoa / Nguyen, Ha / Duong, Duc / Vu, Quan (2008): "An empirical study of multipass decoding for vietnamese LVCSR", In SLTU-2008, 12-17.