paper-with-me

홈 › Papers

ASR Under Noise: Exploring Robustness for Sundanese and Javanese

2025-09-30 · Salsabila Zahirah Pranida, Muhammad Cendekia Airlangga, Rifo Ahmad Genadi, Shady Shehata 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

📄 PDF Abstract BibTeX arXiv:2509.25878

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese

2024-01-12 · Panji Arisaputra, Alif Tri Handoyo, Amalia Zahra

This research paper focuses on the development and evaluation of Automatic Speech Recognition (ASR) technology using the XLS-R 300m model. The study aims to improve ASR performance in converting spoken language into writ…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DiversityLanguage Modeling+3

Building Open Javanese and Sundanese Corpora for Multilingual Text-to-Speech

2018-05-01 · LREC 2018 5 · Jaka Aris Eko Wibawa, Supheakmungkol Sarin, Chenfang Li, Knot Pipatsrisawat 외
Automatic Speech Recognition (ASR)Speech RecognitionSpeech Synthesistext-to-speech+1

IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation

2021-04-16 · EMNLP 2021 11 · Samuel Cahyawijaya, Genta Indra Winata, Bryan Wilie, Karissa Vincentio 외

Natural language generation (NLG) benchmarks provide an important avenue to measure progress and develop better NLG systems. Unfortunately, the lack of publicly available NLG benchmarks for low-resource languages poses a…

Machine TranslationQuestion AnsweringText GenerationTranslation

Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages

2016-10-01 · Nur Endah Safitri, Amalia Zahra, and Mirna Adriani

Research in the field of spoken language identification (spoken LID) on local languages helps to extend the outreach of technology to local language speakers. This research also contributes to the preservation of local …

Language IdentificationLanguage ModellingSpoken language identification

IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages

2023-11-21 · Muhammad Farid Adilazuarda, Samuel Cahyawijaya, Genta Indra Winata, Pascale Fung 외

Significant progress has been made on Indonesian NLP. Nevertheless, exploration of the code-mixing phenomenon in Indonesian is limited, despite many languages being frequently mixed with Indonesian in daily conversation.…

Diversity