Nhut Minh Pham, Vũ Hải Quân


This paper presents the adoption of state-of-the-art ASR techniques into Vietnamese. To better assess these techniques, speech corpora in the research community are assembled, and expanded, making a unified evaluation material under the name VN-Corpus. On this corpus, three ASR systems are built using the conventional HMM-GMM recipe, SGMM, and DNN respectively. Experimental results crown DNN with the overall WER of 12.1%. In the best case, DNN even cut down to 9.7% error rate.


Vietnamese automatic speech recognition; transcription system

Full Text:



Quan Vu, et al., “A Robust Vietnamese Voice Server for Automated Directory Assistance Application,” RIVF-VLSP, HCM City, Viet Nam, 2012.

Quan Vu, et al., “iSago: The Vietnamese Mobile Speech Assistant for Food-court and Restaurant Location,” RIVF-VLSP, HCM City, Viet Nam, 2012.

S. Young, "HMMs and Related Speech Recognition Technologies." Springer Handbook of Speech Processing, Springer, 2007.

D. Povey, et al., “Subspace Gaussian mixture models for speech recognition,” Proceedings of ICASSP’10, 2010.

G. Hinton, et al. "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups." Signal Processing Magazine, IEEE 29.6, pp. 82-97, 2012.

P. Hoang, Syllable Dictionary, Danang Publishing House, 1996.

Quan Vu, et al., “Advances in Acoustic Modeling for Vietnamese LVCSR,” International Conference on Asian Language Processing, Singapore, 2009.

Quan Vu, et al., “A Robust Transcription System for Soccer Video Database,” International Conference on Audio Language and Image Processing (ICALIP), 2010.

Quan Vu, et al., "Temporal confusion network for speech-based soccer event retrieval," International Conference on Advanced Technologies for Communications (ATC), 2013.

H. Nguyen, et al., “Selection of Basic Units for Vietnamese Large Vocabulary Continuous Speech Recognition,” The 4th IEEE International Conference on Computer Science - Research, Innovation and Vision of the Future, HCMC, Vietnam, 2006.

D. Povey and G. Saon, “Feature and model space feature adaptation with full covariance gaussian,” Proceedings of the 9th International Conference on Spoken Language Processing (ICSLP), pp. 4330–4333, 2006.

F. Seide, G. Li, X. Chien, and D. Yu, “Feature engineering in context- dependent deep neural networks for conversational speech transcription,” Proceedings of Automatic Speech Recognition and Understanding Workshop (ASRU), 2011.

DOI: Display counter: Abstract : 241 views. PDF : 124 views.


Journal of Computer Science and Cybernetics ISSN: 1813-9663

Published by Vietnam Academy of Science and Technology