Metraipolis › archive › dc_aff61132bb85

Acoustic and Lexical Signals for Native Language Identification of Language Learners — arXiv:2610.32382

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32382
License (as archived)
CC0-1.0
Archived
2026-10-26T19:53:35.616Z
SHA-256 of the archived text
10665f5ec6c3df0845efc233d4c634417002924f54514ea27f2b3b22f8a1247c
Stable URL of this page
https://metraipolis.com/documento/dc_aff61132bb85

How to cite

Acoustic and Lexical Signals for Native Language Identification of Language Learners — arXiv:2610.32382 — arXiv (en), https://arxiv.org/abs/2610.32382 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aff61132bb85 (Metraipolis archive dc_aff61132bb85, sha256 10665f5ec6c3df0845efc233d4c634417002924f54514ea27f2b3b22f8a1247c)
BibTeX
@misc{dcaff61132bb85,
  title = {Acoustic and Lexical Signals for Native Language Identification of Language Learners — arXiv:2610.32382},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32382},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aff61132bb85; sha256 10665f5ec6c3df0845efc233d4c634417002924f54514ea27f2b3b22f8a1247c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32382. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.32382 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-26T19:45:48.359Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).