Automated evaluation of children's speech fluency for low-resource languages
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912665496977408 |
|---|---|
| author | Zhang, Bowen Latiff, Nur Afiqah Abdul Kan, Justin Tong, Rong Soh, Donny Miao, Xiaoxiao McLoughlin, Ian |
| author_facet | Zhang, Bowen Latiff, Nur Afiqah Abdul Kan, Justin Tong, Rong Soh, Donny Miao, Xiaoxiao McLoughlin, Ian |
| contents | Assessment of children's speaking fluency in education is well researched for majority languages, but remains highly challenging for low resource languages. This paper proposes a system to automatically assess fluency by combining a fine-tuned multilingual ASR model, an objective metrics extraction stage, and a generative pre-trained transformer (GPT) network. The objective metrics include phonetic and word error rates, speech rate, and speech-pause duration ratio. These are interpreted by a GPT-based classifier guided by a small set of human-evaluated ground truth examples, to score fluency. We evaluate the proposed system on a dataset of children's speech in two low-resource languages, Tamil and Malay and compare the classification performance against Random Forest and XGBoost, as well as using ChatGPT-4o to predict fluency directly from speech input. Results demonstrate that the proposed approach achieves significantly higher accuracy than multimodal GPT or other methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automated evaluation of children's speech fluency for low-resource languages Zhang, Bowen Latiff, Nur Afiqah Abdul Kan, Justin Tong, Rong Soh, Donny Miao, Xiaoxiao McLoughlin, Ian Sound Artificial Intelligence Audio and Speech Processing Assessment of children's speaking fluency in education is well researched for majority languages, but remains highly challenging for low resource languages. This paper proposes a system to automatically assess fluency by combining a fine-tuned multilingual ASR model, an objective metrics extraction stage, and a generative pre-trained transformer (GPT) network. The objective metrics include phonetic and word error rates, speech rate, and speech-pause duration ratio. These are interpreted by a GPT-based classifier guided by a small set of human-evaluated ground truth examples, to score fluency. We evaluate the proposed system on a dataset of children's speech in two low-resource languages, Tamil and Malay and compare the classification performance against Random Forest and XGBoost, as well as using ChatGPT-4o to predict fluency directly from speech input. Results demonstrate that the proposed approach achieves significantly higher accuracy than multimodal GPT or other methods. |
| title | Automated evaluation of children's speech fluency for low-resource languages |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.19671 |