arXiv cs.CL· Ahmet Yavuz Uluslu, Mengjie Qian, Kate Knill, Mark Gales·· 12 小时前AI 评分18
基于声学与词汇信号识别语言学习者的母语
Acoustic and Lexical Signals for Native Language Identification of Language Learners
AI 导读
研究对比了基于 WavLM 的音频母语识别分类器与零样本 GPT-4o 转写文本分类器，在 CEFR 均衡评测集上，完整转写文本下音频分类器整体更优。音频在 A1 水平表现更好，文本在 A2 至 C1 水平更优，且文本准确率随水平提升而上升，声学表现相对稳定。限制转写长度会显著降低文本准确率，而音频对输入长度较不敏感。
正文 · 原文
Abstract:Spoken native language (L1) identification for second language learners has traditionally relied on acoustic attributes of speech. Comparatively little attention has been paid to analysing speech transcripts for L1 traces. In this paper, we present a study of L1 identification using both speech and corresponding transcripts from a spoken learner English corpus. We compare a WavLM-based audio L1 classifier with a zero-shot GPT-4o classifier operating on transcripts and analyse their predictions across proficiency levels using a CEFR-balanced evaluation set. Our experiments show that the audio classifier outperforms the transcript-based approach overall when full transcripts are available, although their relative strengths vary with learner proficiency. Audio performs better at A1, whereas text performs better from A2 to C1 with full transcripts. Transcript-based accuracy generally increases with proficiency, while acoustic performance remains comparatively stable. Restricting transcript length substantially reduces text-based accuracy, whereas audio is less sensitive to input length and performs relatively well with limited input. These findings provide insights into L1 identification from acoustic and textual representations of learner speech and how performance varies with proficiency and the amount of available language material.
| Comments: | Accepted for publication at NLP4CALL |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.32382 [cs.CL] |
| (or arXiv:2610.32382v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32382 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mengjie Qian [view email]
[v1]
Fri, 23 Oct 2026 09:11:49 UTC (294 KB)
来源：arXiv cs.CL · arxiv.org