ASR Under Noise: Exploring Robustness for Sundanese and Javanese
Not on the map. Why?
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
Key facts. Cited by 1 paper 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
9 of 25 references.
References · 9
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
- 2020Rethinking Evaluation in ASR: Are Our Models Robust Enough?cited by 73
- 2022NusaCrowd: Open Source Initiative for Indonesian NLP Resourcescited by 38
- 2024Speech Robust Bench: A Robustness Benchmark For Speech Recognitioncited by 21
- 2021ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understandingcited by 9
- 2024Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Networkcited by 4
- 2024XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanesecited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.