Stuttering-Aware Automatic Speech Recognition for Indonesian Language
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912822460416000 |
|---|---|
| author | Muhammad, Fadhil Djuliansah, Alwin Hamzah, Adrian Aryaputra Azizah, Kurniawati |
| author_facet | Muhammad, Fadhil Djuliansah, Alwin Hamzah, Adrian Aryaputra Azizah, Kurniawati |
| contents | Automatic speech recognition systems have achieved remarkable performance on fluent speech but continue to degrade significantly when processing stuttered speech, a limitation that is particularly acute for low-resource languages like Indonesian where specialized datasets are virtually non-existent. To overcome this scarcity, we propose a data augmentation framework that generates synthetic stuttered audio by injecting repetitions and prolongations into fluent text through a combination of rule-based transformations and large language models followed by text-to-speech synthesis. We apply this synthetic data to fine-tune a pre-trained Indonesian Whisper model using transfer learning, enabling the architecture to adapt to dysfluent acoustic patterns without requiring large-scale real-world recordings. Our experiments demonstrate that this targeted synthetic exposure consistently reduces recognition errors on stuttered speech while maintaining performance on fluent segments, validating the utility of synthetic data pipelines for developing more inclusive speech technologies in under-represented languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03727 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stuttering-Aware Automatic Speech Recognition for Indonesian Language Muhammad, Fadhil Djuliansah, Alwin Hamzah, Adrian Aryaputra Azizah, Kurniawati Computation and Language Automatic speech recognition systems have achieved remarkable performance on fluent speech but continue to degrade significantly when processing stuttered speech, a limitation that is particularly acute for low-resource languages like Indonesian where specialized datasets are virtually non-existent. To overcome this scarcity, we propose a data augmentation framework that generates synthetic stuttered audio by injecting repetitions and prolongations into fluent text through a combination of rule-based transformations and large language models followed by text-to-speech synthesis. We apply this synthetic data to fine-tune a pre-trained Indonesian Whisper model using transfer learning, enabling the architecture to adapt to dysfluent acoustic patterns without requiring large-scale real-world recordings. Our experiments demonstrate that this targeted synthetic exposure consistently reduces recognition errors on stuttered speech while maintaining performance on fluent segments, validating the utility of synthetic data pipelines for developing more inclusive speech technologies in under-represented languages. |
| title | Stuttering-Aware Automatic Speech Recognition for Indonesian Language |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.03727 |