The NNi Vietnamese speech recognition system for mediaeval 2016

• Main Authors: Xiao, Xiong, Nwe, Tin Lay, Chng, Eng Siong, Ma, Bin, Li, Haizhou, Wang, Lei, Ni, Chongjia, Leung, Cheung-Chi, You, Changhuai, Xie, Lei, Xu, Haihua
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2019
• Subjects: Vietnamese; Recognition; DRNTU::Engineering::Computer science and engineering
• Online Access: https://hdl.handle.net/10356/79851; http://hdl.handle.net/10220/48316; http://ceur-ws.org/Vol-1739/MediaEval_2016_paper_52.pdf
• Institution: Nanyang Technological University

This paper provides an overall description of the Vietnamese speech recognition system developed by the joint team for MediaEval 2016. The submitted system consisted of 3 subsystems, and adopted different deep neural network-based techniques such as fMLLR transformed bottleneck features, sequence training, etc. Besides the acoustic modeling techniques, speech data augmentation was also examined to develop a more robust acoustic model. The I2R team collected a number of text resources from the Internet and made them available to other participants in the task. The web text crawled from the Internet was used to train a 5-gram language model. The submitted system obtained the token error rate (TER) of 15.1, 23.0 and 50.5 on Devel local set, Devel set and Test set, respectively.