Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Indonesian Journal of Data and Science
Desi Fatkhi Azizah
Universitas Negeri Malang
Computer Science & IT Decision Sciences, Operations Research & Management Engineering Mathematics

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparative Analysis of Speech-to-Text APIs for Supporting Communication of the Deaf Community Anik Nur Handayani; Hariyono Hariyono; Ahmad Munjin Nasih; Rochmawati Rochmawati; Imanuel Hitipeuw; Harits Ar Rosyid; Jevri Tri Ardiansah; Rafli Indar Praja; Ahmad Nurdiansyah; Desi Fatkhi Azizah
Indonesian Journal of Data and Science Vol. 6 No. 3 (2025): Indonesian Journal of Data and Science
Publisher : yocto brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v6i3.327

Abstract

Hearing impairment can have a profound impact on the mental and emotional state of sufferers, as well as hinder communication and delay in accessing information directly that relies on interpreters. Advances in assistive technology, especially speech recognition systems that are able to convert spoken language into written text (speech-to-text). However, its implementation faces various challenges related to the level of accuracy of each speech-to-text Application Programming Interface (API), thus requiring an appropriate deep learning model. This study serves to analyze and compare the performance of speech-to-text API services (Deepgram API, Google API and Whisper AI) based on Word Error Rate (WER) and Words Per Minute (WPM), to determine the most optimal API in a web-based real-time transcription system using the JavaScript programming language and Glitch.com. The three API services were tested by calculating their error rates and transcription speeds, then evaluated to see how low the error accuracy rate was and how high the transcription speed was. On average, Whisper AI had a WER of 0% across all word categories, but its speed was lower than the other two APIs. Deepgram API displayed the best balance between accuracy and speed, with an average WER of 13.78% and 67 WPM. Google API performed stably, but its WER value was slightly higher than Deepgram API. In conclusion, based on the results, Deepgram API was deemed the most optimal for live transcription, as it is capable of producing fast and error-free transcriptions, significantly increasing the accessibility of information for the deaf community.
Comparative Analysis of YOLOv8 Segmentation Variants for Indonesian Sign Language (SIBI) Recognition Desi Fatkhi Azizah; Anik Nur Handayani; Aji Prasetya Wibawa; Osamu Fukuda
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 2 (2026): April 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i2.7500

Abstract

The Indonesian Sign Language System (SIBI) is the officially recognized communication medium for deaf communities in Indonesia, yet its limited public use continues to create barriers in education, healthcare, and public services. Automatic sign language recognition powered by artificial intelligence provides a promising pathway to reduce these inequities. This study presents a comprehensive comparative evaluation of YOLOv8 segmentation variants for SIBI recognition, aiming to identify models that stabilize accuracy and efficiency for real-time deployment. A mono-background dataset of SIBI alphabet gestures was annotated using instance segmentation, and five YOLOv8-seg models (n, s, m, l, x) were trained and tested across multiple data-split scenarios. Performance was assessed through precision, recall, F1-score, mAP50, mAP50–95, and inference time. Results show that YOLOv8m-seg consistently achieved the best trade-off (F1-score 0.972; mAP50 0.982), while YOLOv8n-seg delivered the fastest inference speed (5.163 ms), making it suitable for resource-constrained devices. Visualization further demonstrated the models’ ability to capture hand contours and distinguish gestures accurately. Beyond technical benchmarking, this research highlights the potential of YOLOv8-based SIBI recognition as an inclusive assistive technology for bridging communication gaps in schools and clinics where interpreters are often unavailable. It also identifies governance challenges, including privacy protection, misclassification risks, and equitable access, which must be addressed for actual adoption. The findings, therefore, provide not only a contribution to computer vision research but also practical guidance for policymakers and service providers, positioning SIBI recognition systems as socially embedded technologies aligned with the goals of disability inclusion and sustainable development.
Co-Authors Ahmad Munjin Nasih Ahmad Nurdiansyah Aji Prasetya Wibawa Anik Nur Handayani Harits Ar Rosyid Hariyono Hariyono Imanuel Hitipeuw Jevri Tri Ardiansah Osamu Fukuda Rafli Indar Praja Rochmawati Rochmawati