Accesso libero

Language model optimization and corpus construction techniques for Japanese speech recognition

Zhou Huang

Zhou Huang

School of Oriental Languages, Anhui International Studies UniversityHefei, China
Cerca questo autore su
Sciendo|Google Scholar
Huang, Zhou
 e 
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
Cerca questo autore su
Sciendo|Google Scholar
Cao, Yang
  
21 mar 2025
Language model optimization and corpus construction techniques for Japanese speech recognition's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Pubblicato online: 21 mar 2025
Ricevuto: 08 nov 2024
Accettato: 24 feb 2025
DOI: https://doi.org/10.2478/amns-2025-0697
Parole chiave
© 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
Lingua:
Inglese
Frequenza di pubblicazione:
1 volte all'anno
Argomenti della rivista:
Scienze biologiche, Scienze della vita, altro, Matematica, Matematica applicata, Matematica generale, Fisica, Fisica, altro
Feed RSS della rivista