Metraipolis › archive › dc_a9cc36f55def
Speaker Verification Under Real Classroom Conditions for English Speech — arXiv:2608.03623
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03623
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T13:28:53.340Z
- SHA-256 of the archived text
d6f5a5dc2b8642937699cab33611810ae7e579dd4ed978f3b564e0250c90eb4b- Stable URL of this page
https://metraipolis.com/documento/dc_a9cc36f55def
How to cite
Speaker Verification Under Real Classroom Conditions for English Speech — arXiv:2608.03623 — arXiv (en), https://arxiv.org/abs/2608.03623 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a9cc36f55def (Metraipolis archive dc_a9cc36f55def, sha256 d6f5a5dc2b8642937699cab33611810ae7e579dd4ed978f3b564e0250c90eb4b)
BibTeX
@misc{dca9cc36f55def,
title = {Speaker Verification Under Real Classroom Conditions for English Speech — arXiv:2608.03623},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03623},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a9cc36f55def; sha256 d6f5a5dc2b8642937699cab33611810ae7e579dd4ed978f3b564e0250c90eb4b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03623. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Developing speaker verification (SV) models that are robust to classroom noise and effective across both children and adult speakers is critical for AI tools supporting educational environments. In this study, we use a real-world English-speaking classrooms dataset containing partial speaker identity annotations, with most recordings remaining unlabeled. We adapt the WavLM-TDNN model for classroom SV, achieving average relative reductions in Equal Error Rate (EER) of 23.99% and 6.32% compared to the ECAPA-TDNN baseline and the ECAPA-TDNN model trained on classroom data, respectively. Additionally, we investigate two training strategies for SV in classroom settings: self-supervised learning (SSL) and a two-stage approach that first pre-trains with SSL and then fine-tunes with limited annotated data. Five-fold cross-validation demonstrates that the two-stage strategy consistently outperforms the SSL-only approach, achieving an average relative EER reduction of 13.39%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in eess.AS). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2608.03623 — 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 2026-10-31T13:15:28.099Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).