Improving Hybrid CTC/Attention Architecture for Agglutinative Language Speech Recognition

Unlike the traditional model, the end-to-end (E2E) ASR model does not require speech information such as a pronunciation dictionary, and its system is built through a single neural network and obtains performance comparable to that of traditional methods. However, the model requires massive amounts...

Descripción completa

Detalles Bibliográficos
Autores principales: Ren, Zeyu, Yolwas, Nurmemet, Slamu, Wushour, Cao, Ronghe, Wang, Huiru
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9571619/
https://www.ncbi.nlm.nih.gov/pubmed/36236419
http://dx.doi.org/10.3390/s22197319

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9571619/
https://www.ncbi.nlm.nih.gov/pubmed/36236419
http://dx.doi.org/10.3390/s22197319

Ejemplares similares