Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.14744 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908779495292928 |
|---|---|
| author | Liu, Hongfu Cui, Zhouying Gu, Xiangming Wang, Ye |
| author_facet | Liu, Hongfu Cui, Zhouying Gu, Xiangming Wang, Ye |
| contents | Achieving pronunciation proficiency in a second language (L2) remains a challenge, despite the development of Computer-Assisted Pronunciation Training (CAPT) systems. Traditional CAPT systems often provide unintuitive feedback that lacks actionable guidance, limiting its effectiveness. Recent advancements in audio-language models (ALMs) offer the potential to enhance these systems by providing more user-friendly feedback. In this work, we investigate ALMs for chat-based pronunciation training by introducing L2-Arctic-plus, an English dataset with detailed error explanations and actionable suggestions for improvement. We benchmark cascaded ASR+LLMs and existing ALMs on this dataset, specifically in detecting mispronunciation and generating actionable feedback. To improve the performance, we further propose to instruction-tune ALMs on L2-Arctic-plus. Experimental results demonstrate that our instruction-tuned models significantly outperform existing baselines on mispronunciation detection and suggestion generation in terms of both objective and human evaluation, highlighting the value of the proposed dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14744 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unlocking Large Audio-Language Models for Interactive Language Learning Liu, Hongfu Cui, Zhouying Gu, Xiangming Wang, Ye Sound Audio and Speech Processing Achieving pronunciation proficiency in a second language (L2) remains a challenge, despite the development of Computer-Assisted Pronunciation Training (CAPT) systems. Traditional CAPT systems often provide unintuitive feedback that lacks actionable guidance, limiting its effectiveness. Recent advancements in audio-language models (ALMs) offer the potential to enhance these systems by providing more user-friendly feedback. In this work, we investigate ALMs for chat-based pronunciation training by introducing L2-Arctic-plus, an English dataset with detailed error explanations and actionable suggestions for improvement. We benchmark cascaded ASR+LLMs and existing ALMs on this dataset, specifically in detecting mispronunciation and generating actionable feedback. To improve the performance, we further propose to instruction-tune ALMs on L2-Arctic-plus. Experimental results demonstrate that our instruction-tuned models significantly outperform existing baselines on mispronunciation detection and suggestion generation in terms of both objective and human evaluation, highlighting the value of the proposed dataset. |
| title | Unlocking Large Audio-Language Models for Interactive Language Learning |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.14744 |