Aug 2026· Bulletin of Electrical Engineering and Informatics· 0 citations· 25 references
TL;DR
Findings indicate that language-specific fine-tuning plays a more critical role than multilingual generalization in achieving accurate ASR for Indonesian and provide practical guidance for deploying ASR systems in low-resource language scenarios.
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.
This study presents the development of an automatic speech recognition (ASR) system tailored for Telugu, one of the widely spoken Indian languages. In recent years, deep learning (DL) techniques have been applied to develop ASR systems across various languages and domains. These models, however, require substantial training resources and extensive corpora of continuous speech composed from multiple dialectal speakers, along with their corresponding transcripts. This paper investigates the effectiveness of pre-trained models like Wav2Vec XLSR-53 and Whisper-Small for developing ASR systems for the Telugu language, addressing the challenge of limited data availability and demonstrating satisfactory results even when fine-tuned on a smaller dataset. We utilized approximately 20 h of speech data comprising 17,421 sentences of the Telugu language. The models are fine-tuned on four publicly available datasets, including OpenSLR, Common Voice, IndicVoices, and IndicTTS, to introduce greater diversity in both speaker demographics and linguistic content. The Wav2Vec XLSR-53 model achieved a word error rate (WER) of 27.3% and a character error rate (CER) of 6.8% on the test dataset, whereas the Whisper-Small attained a WER of 28.67% and a CER of 7.55%. In addition, performance of the models was evaluated by introducing noise to both individual datasets as well as a combined noise dataset. The results show that, on the combined noise dataset, Wav2Vec XLSR-53 achieved a WER of 19.59% and a CER of 4.58%, while Whisper Small obtained a lower WER of 13.97% and a CER of 3.54%. These results underscore the usefulness of leveraging pre-trained architectures in low-resource linguistic scenarios such as Telugu.
J. Pushparaj, Muzaffar Ahmad Dar, Sri Gani Kaarthikeya Kammula et al.· Frontiers in Artificial Inte...· 0 citations
This study reports the development of an Automatic Speech Recognition (ASR) system in Mizo, a low-resource language. The development included collecting 17.62 hours of speech data, curating it, and fine-tuning the Mizo ASR system with three Whisper multilingual models and with the SraVaani 1.0 Indic multilingual model. Whisper-large-v3 achieved the lowest conventional WER (18.08%), while morphology-aware evaluation yielded a WER of 7.22%. Zero-shot evaluation of the SraVaani 1.0 Indic multilingual model yielded a WER of 58.27%, while Mizo-specific fine-tuning reduced the conventional WER to 29.45% and the morphology-aware WER to 17.93%. The results demonstrate that the Whisper model can achieve a substantially low WER, even when adapted to an unseen language. In contrast, SraVaani 1.0 supports the Mizo language in its multilingual model; however, fine-tuning with carefully curated Mizo speech data substantially improves its performance.
A reproducible, multi-metric benchmarking framework for systematic evaluation of modern TTS systems through domain-specific analysis, which reveals substantial variation in TTS performance across speech domains, with emotional speech consistently presenting the greatest synthesis challenge.
Ali B. Jafar, Amal Sarmad, Shifa Yousaf et al.· 0 citations
Detecting hate speech in low-resource and unseen languages remains challenging due to limited labeled data and linguistic diversity. This paper presents a comparative study of zero-shot cross-lingual transfer for hate speech detection using two multilingual transformer models: mDeBERTa-v3 and XLM-RoBERTa. To the best of our knowledge, mDeBERTa-v3 has not been previously used by researchers for zero-shot cross-lingual hate speech detection, making this the first study to evaluate its capabilities in this task. Furthermore, we introduce new unseen languages that have not been studied before in this context, including Hebrew, Amharic, and Swahili, alongside other languages such as Indonesian, Danish Portuguese, Turkish, French, and Russian. We evaluate model performance under three training scenarios: a single source language (Turkish), semantically similar language clusters, and multiple clusters from different language families. Experimental results show that mDeBERTa-v3 consistently outperforms XLM-RoBERTa in zero-shot settings. The most notable improvement is observed for Hebrew, where the macro F1 score increases from 0.39 (XLM-RoBERTa) to 0.71 (mDeBERTa-v3), a gain of 0.32. Substantial gains are also seen for Amharic (0.52 → 0.73, +0.21), Indonesian (0.57 → 0.71, +0.14), and Swahili (0.65 → 0.75, +0.10). Across all experimental conditions, mDeBERTa-v3 achieves average macro F1 gains ranging from 0.04 to 0.19, with statistical significance (p < 0.02). The model’s advantage is attributed to its disentangled attention mechanism, which enables better generalization across typologically distant languages. These findings establish mDeBERTa-v3 as a novel and more robust architecture for zero-shot cross-lingual hate speech detection, particularly for previously unexplored low-resource languages.
Ghadeer Al-Badani, M. Alsurori, Akram Alsubari· 2026 6th International Confe...· 0 citations
SraVaani-1.0 achieves the lowest word error rate (WER) on a large number of language-dataset pairs while remaining competitive with the best-performing systems on high resource while being assessed exclusively on the VAANI benchmark.
Sujith Pulikodan, A. Basu, J. Pavankumar et al.· 1 citation· ⚡1
A preliminary study on the adaptation of Whisper for Automatic Speech Recognition in Baniwa, an indigenous Arawakan language spoken in Brazil, Colombia, and Venezuela, demonstrating that multilingual foundation models can be successfully adapted to extremely low-resource indigenous languages.
Leonardo Duart, T. Fonseca, T. Chacon· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
