Article Per Year (5 Year)
p-Index From 2021 - 2026
2.293
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Bulletin of Electrical Engineering and Informatics Jurnal Informatika dan Teknik Elektro Terapan Syntax Idea Computer Science and Information Technologies
Amalia Zahra
Bina Nusantara University
Aerospace Engineering Agriculture, Biological Sciences & Forestry Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Electrical & Electronics Engineering Engineering

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Javanese and Sundanese speech recognition using Whisper Alim Raharjo; Amalia Zahra
Computer Science and Information Technologies Vol 6, No 3: November 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/csit.v6i3.p253-261

Abstract

Automatic speech recognition (ASR) technology is essential for advancing human-computer interaction, particularly in a linguistically diverse country like Indonesia, where approximately 700 native languages are spoken, including widely used languages like Javanese and Sundanese. This study leverages the pre-trained Whisper Small model an end‑to‑end transformer pretrained on 680,000 hours of multilingual speech, fine tuning it specifically to improve ASR performance for these low resource languages. The primary goal is to increase transcription accuracy and reliability for Javanese and Sundanese, which have historically had limited ASR resources. Approximately 100 hours of speech from OpenSLR were selected, covering both reading and conversational prompts, the data exhibited dialectal variation, ambient noise, and incomplete demographic metadata, necessitating normalization and fixed‑length padding. with model evaluation based on the word error rate (WER) metric. Unlike approaches that combine separate acoustic encoders with external language models, Whisper unified architecture streamlines adaptation for low‑resource settings. Evaluated on held‑out test sets, the fine‑tuned models achieved Word Error Rates of 14.97% for Javanese and 2.03% for Sundanese, substantially outperforming baseline systems. These results demonstrate Whisper effectiveness in low‑resource ASR and highlight its potential to enhance transcription accuracy, support language preservation, and broaden digital access for underrepresented speech communities. 
Speech emotion recognition with optimized multi-feature stack using deep convolutional neural networks Muhammad Farhan Fadhil; Amalia Zahra
Bulletin of Electrical Engineering and Informatics Vol 13, No 6: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i6.6044

Abstract

The human emotion in communication plays a significant role that can influence how the context of the message is perceived by others. Speech emotion recognition (SER) is one of a field study that is very intriguing to explore because human-computer interaction (HCI) related technologies such as virtual assistant that are implemented nowadays rarely considered the emotion contained in the information relayed by human speech. One of the most widely used ways to perform SER is by extracting features of speech such as mel frequency cepstral coefficient (MFCC), mel-spectrogram, spectral contrast, tonnetz, and chromagram from the signal and using a one-dimensional (1D) convolutional neural network (CNN) as a classifier. This study shows the impact of implementing a combination of an optimized multi-feature stack and optimized 1D deep CNN model. The result of the model proposed in this study has an accuracy of 90.10% for classifying 8 different emotions performed on the ryerson audio-visual database of emotional speech and song (RAVDESS) dataset.
Speech-to-text model comparison using XLS-R, XLSR-53, and Wav2Vec 2.0 Juan Hebert; Amalia Zahra
Bulletin of Electrical Engineering and Informatics Vol 15, No 4: August 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i4.11431

Abstract

Automatic speech recognition (ASR) systems have achieved significant progress in recent years; however, their performance remains limited for low-resource languages such as Indonesian. Multilingual ASR models are often expected to generalize across languages, yet they frequently underperform when applied to underrepresented languages without sufficient adaptation. This study presents a comparative evaluation of three ASR models—Wav2Vec 2.0, XLS-R, and XLSR-53—on Indonesian speech to analyze the impact of monolingual fine-tuning versus multilingual pretraining. The evaluation was conducted using approximately 28 hours of validated Indonesian speech from the Common Voice Corpus version 13. Model performance was assessed using word error rate (WER) without employing any external language model to ensure a fair comparison. Experimental results demonstrate that Wav2Vec 2.0, which is fine-tuned specifically for Indonesian, achieves substantially lower WER compared to the multilingual models. Qualitative analysis further confirms that multilingual models exhibit higher omission and substitution errors. These findings indicate that language-specific fine-tuning plays a more critical role than multilingual generalization in achieving accurate ASR for Indonesian. The results provide practical guidance for deploying ASR systems in low-resource language scenarios and highlight the importance of targeted model adaptation.
Co-Authors Agusti Frananda Alfonsus Naibaho Ahmad Iqbal Abdurrahman Alim Raharjo Bhakti Prabandyo Wicaksono Francisco Calvin Arnel Ferano Gede Putra Kusuma Jonathan Christian Setyono Juan Hebert Kristian Handoko Wijaya Sukardjoh Muhammad Farhan Fadhil Randy Himawan Satrio Sadewo Wijonarko, Panji Yoga Tanoko