VIVOS CorpusVIVOS is a free Vietnamese speech corpus consisting of 15 hours of recording speech prepared for Automatic Speech Recognition task. The corpus was prepared by AILAB, a computer science lab of VNUHCM - University of Science, with Prof. Vu Hai Quan is the head of. We publish this corpus in hope to attract more scientists to solve Vietnamese speech recognition problems. The corpus should only be used for academic purposes. License Creative Commons Attribution NonCommercial ShareAlike v4.0 (CC BY-NC-SA 4.0) (details) Download corpus Associated paper "A non-expert Kaldi recipe for Vietnamese Speech Recognition System", Hieu-Thi Luong and Hai-Quan Vu, in Proc. WLSI-3 & OIAF4HLT-2 (pdf) Contact |
Corpus propertiesSpeech was recorded in a quiet enviroment with high quality microphone, speakers were asked to read one sentence at a time.
|
baseline | +pitch | +tone | |
---|---|---|---|
mGMM | 19.66 | 15.14 | 14.91 |
mGMM+MMI | 18.08 | 14.96 | 13.91 |
mGMM+SAT | 15.79 | 12.07 | 12.13 |
mDNN+SAT | 13.34 | 9.54 | 9.48 |