Fast offline transformer-based end-to-end automatic speech recognition for real-world applications

With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more vital than ever. In this study, we propose a method to rapidly...

Descripción completa

Detalles Bibliográficos

Autores principales:	Yoo Rhee Oh, Kiyoung Park
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	Electronics and Telecommunications Research Institute (ETRI) 2022-06-01
Colección:	ETRI Journal
Materias:	connectionist temporal classification end-to-end speech recognition transformer
Acceso en línea:	https://doi.org/10.4218/etrij.2021-0106
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!