AUTOMATIC SPEECH RECOGNITION SYSTEM FOR KAZAKH LANGUAGE USING CONNECTIONIST TEMPORAL CLASSIFIER

YEDILKHAN AMIRGALIYEV; DARKHAN KUANYSHBAY; DIDAR YEDILKHAN; SHOIYNBEK A

No Detail Found!

AUTOMATIC SPEECH RECOGNITION SYSTEM FOR KAZAKH LANGUAGE USING CONNECTIONIST TEMPORAL CLASSIFIER

Author(s)

YEDILKHAN AMIRGALIYEV Institute of Information and Computational Technologies CS MES RK, Kazakhstan; Al-Farabi Kazakh National University, Kazakhstan

DARKHAN KUANYSHBAY Institute of Information and Computational Technologies CS MES RK, Kazakhstan; Suleyman Demirel University, Kazakhstan

DIDAR YEDILKHAN Suleyman Demirel University, Kazakhstan; Institute of Information and Computational Technologies CS MES RK, Kazakhstan

SHOIYNBEK A Institute of Information and Computational Technologies CS MES RK, Kazakhstan; Astana IT University, Kazakhstan

Abstract

This scientific report illustrates the performance evaluation of the well-known, recently popular neural network Connectionist Temporal Classifier (CTC) for speech recognition. The CTC contains LSTM layers with 256 cells and Momentum Optimizer with learning rate 0.005 and momentum 0.9. Dataset that we have used has 35 native speakers with 360 utterances. For expanding the size of our dataset with overall performance augmentation techniques has been applied using Adobe Audition software, which output 20 more speakers to our original dataset. The result of our experiment has been evaluated with LER (Label error rate). LER measures the inaccuracy between predicted an actual texts. The output of the experiment reported training LER 0.000 and validation LER 0.5.

Publication Details

Page(s) 703-713

DOI DOI not available

Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 98, Issue: 4, Year: 2020

Request the full text from PASTIC

Keywords

CTC, Acoustic Model, Language Model, Data Augmentation, Time Warping.

Citations

Downloads

Views