Investigating Sibilant Fricative Representation in Bangla Telemedicine Speech: A Cost-Aware Sampling Rate Optimization Study
Signals · 07.05.2026 · 7 (3) · 44
DOI: 10.3390/signals7030044 ↗Kurz gefasst
Fachartikel in der Zeitschrift Signals, online erschienen am 07.05.2026. Verfasst von Prajat Paul und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JST BOOST, JST Startup Ecosystem Co-creation Program for New Industry University Startups.
Abstract (Originalsprache)
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 contains sibilant fricatives and other phonetic cues with substantial high-frequency energy that may be suppressed under bandwidth and latency constraints. This study evaluates audio sampling rate as a controllable signal-level parameter for Bangla telehealth ASR to identify an empirically grounded operating range balancing transcription accuracy, execution time, and network bandwidth. Twenty real-world Bangla doctor–patient consultations were deterministically resampled to 55 configurations between 8 kHz and 32 kHz and transcribed using a fixed cloud-based ASR system. Session-level Word Error Rate, execution latency, payload bandwidth, and high-frequency phonetic content were analyzed using a composite sibilant-likelihood score. WER decreased from 0.338 at 8 kHz to a local minimum of 0.232 at 18.75 kHz, with gains plateauing beyond this range despite substantial bandwidth increases. Elbow-point, Pareto frontier, weighted scoring, and Minimum Acceptable Trade-off analyses converged on an optimal region between 17.25 and 18.75 kHz, demonstrating that sampling rate optimization improves ASR accuracy without proportional resource costs in telehealth settings.
Förderung
- JST BOOST
- JST Startup Ecosystem Co-creation Program for New Industry University Startups
Zitieren
APA
Paul, P., Bouh, M. M., Shah, M. V., Hossain, F., & Ahmed, A. (2026). Investigating Sibilant Fricative Representation in Bangla Telemedicine Speech: A Cost-Aware Sampling Rate Optimization Study. Signals, 7(3), 44. https://doi.org/10.3390/signals7030044
Vancouver
Paul P, Bouh MM, Shah MV, Hossain F, Ahmed A. Investigating Sibilant Fricative Representation in Bangla Telemedicine Speech: A Cost-Aware Sampling Rate Optimization Study. Signals. 2026;7(3):44. doi:10.3390/signals7030044
BibTeX
@article{Paul2026,
author = {Paul, Prajat and Bouh, Mohamed Mehfoud and Shah, Manan Vinod and Hossain, Forhad and Ahmed, Ashir},
title = {Investigating Sibilant Fricative Representation in Bangla Telemedicine Speech: A Cost-Aware Sampling Rate Optimization Study},
journal = {Signals},
year = {2026},
volume = {7},
number = {3},
pages = {44},
doi = {10.3390/signals7030044}
}
EUVIMED