Open Access

Language model optimization and corpus construction techniques for Japanese speech recognition

Zhou Huang

Zhou Huang

School of Oriental Languages, Anhui International Studies UniversityHefei, China
Search for this author on
Sciendo|Google Scholar
Huang, Zhou
 and 
Yang Cao

Yang Cao

  • School of Foreign Languages, Qilu University of Technology (Shandong Academy of Sciences)Jinan, China
  • Graduate School of Humanities, Josai International UniversityTogane, Japan
Search for this author on
Sciendo|Google Scholar
Cao, Yang
  
Mar 21, 2025
Language model optimization and corpus construction techniques for Japanese speech recognition's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Published Online: Mar 21, 2025
Received: Nov 08, 2024
Accepted: Feb 24, 2025
DOI: https://doi.org/10.2478/amns-2025-0697
Keywords
© 2025 Zhou Huang et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

LSTM unit structure
LSTM unit structure

Figure 2.

Model structure based on Bi LSTM-CTC
Model structure based on Bi LSTM-CTC

Figure 3.

Structure of the class based RNN
Structure of the class based RNN

Figure 4.

Language model PPL comparison
Language model PPL comparison

Figure 5.

Results of accuracy rate
Results of accuracy rate

Figure 6.

Loss curve
Loss curve

Figure 7.

The number of parameters and the error rate of the test set
The number of parameters and the error rate of the test set

Figure 8.

Compare it to his model
Compare it to his model
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Life Sciences, Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics, Physics, other
Journal RSS Feed