# ASR Under Noise: Exploring Robustness for Sundanese and Javanese

arXiv: https://arxiv.org/abs/2509.25878 · HTML: https://mlsanity.com/paper/2509.25878/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Rethinking Evaluation in ASR: Are Our Models Robust Enough?](https://mlsanity.com/paper/2010.11745/) (2020)
- [NusaCrowd: Open Source Initiative for Indonesian NLP Resources](https://mlsanity.com/paper/2212.09648/) (2022)
- [Speech Robust Bench: A Robustness Benchmark For Speech Recognition](https://mlsanity.com/paper/2403.07937/) (2024)
- [ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding](https://mlsanity.com/paper/2108.13048/) (2021)
- [Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network](https://mlsanity.com/paper/2406.18928/) (2024)
- [XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese](https://mlsanity.com/paper/2401.06832/) (2024)

## Built on by (most cited first, 1 of 1)

- [myMediWhisper: Construction of Burmese Medical Speech Corpus and Whisper Fine-Tuning for Clinical Dialogue ASR](https://mlsanity.com/paper/2608.11036/) (2026)

## Abstract (arXiv)

We investigate the robustness of Whisper-based automatic speech recognition (ASR) models for two major Indonesian regional languages: Javanese and Sundanese. While recent work has demonstrated strong ASR performance under clean conditions, their effectiveness in noisy environments remains unclear. To address this, we experiment with multiple training strategies, including synthetic noise augmentation and SpecAugment, and evaluate performance across a range of signal-to-noise ratios (SNRs). Our results show that noise-aware training substantially improves robustness, particularly for larger Whisper models. A detailed error analysis further reveals language-specific challenges, highlighting avenues for future improvements