Investigating Sibilant Fricative Representation in Bangla Telemedicine Speech: A Cost-Aware Sampling Rate Optimization Study

Automatic speech recognition has advanced rapidly for high-resource languages, yet performance remains limited for low-resource languages such as Bangla, particularly in telehealth settings. Most systems rely on a standardized 16 kHz sampling rate, a design choice despite evidence that Bangla contai...

Descripció completa

Dades bibliogràfiques

Autors principals:	Prajat Paul, Mohamed Mehfoud Bouh, Manan Vinod Shah, Forhad Hossain, Ashir Ahmed
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2026-05-01
Col·lecció:	Signals
Matèries:	automatic speech recognition (ASR) Bangla Language telehealth Low-Resource Language (LRL) sibilant fricatives word error rate (WER)
Accés en línia:	https://www.mdpi.com/2624-6120/7/3/44
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!