A method for speech Vietnamese recognition based on deep learning
Abstract
Speech recognition has been increasingly applied in various fields such as automatic switchboards, security, searching by voice and so on. However, the quality of recognition is the problem of utmost concern. This paper describes the Speech Vietnamese recognition system built on Kaldi toolkit. The paper also evaluates the quality of system based on evaluating the ratio of the WER on acoustic models. The proposed system achieved superior results compared to previous toolkits on the Vietnamese speech.
How to Cite This Article
Thanh T Nguyen, Binh A Nguyen, Manh Hoang, Tung V Nguyen, Giao N Pham (2021). A method for speech Vietnamese recognition based on deep learning. International Journal of Multidisciplinary Research and Growth Evaluation (IJMRGE), 2(4), 152-156.