arXiv cs.CL· Xu He, Homayoon Beigi·· 6 天前AI 评分17
重新审视 DistilHuBERT 口音分类：说话人分离评估与跨语料泛化
Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization
AI 导读
研究基于 DistilHuBERT 重新评估口音分类鲁棒性，使用 L2-ARCTIC 与多个外部英语口音数据集，对比文件级与说话人分离划分。结果显示文件级评估显著高估性能，说话人分离评估才能更真实反映对未见说话人的泛化能力；仅用外部数据训练的模型无法可靠泛化到 L2-ARCTIC，平衡外部数据训练是最有前景的监督设置，而仅靠置信度过滤的伪标签在域不匹配下不够充分。
正文 · 原文
Abstract:Recent accent classification systems can achieve high accuracy in standard in-corpus evaluations. However, when speakers overlap between the training and test sets, such results may overestimate model robustness compared with real-world deployment scenarios. This study revisits the robustness of DistilHuBERT-based accent classification by using L2-ARCTIC and multiple external English accent datasets. The comparison covers file-level and speaker-disjoint splits, along with balanced external-data training and teacher-student pseudo-labeling. The large performance gap between in-corpus and external evaluations suggests that file-level evaluation substantially overestimates performance, while speaker-disjoint evaluation can provide a more realistic estimate of the generalization to unseen speakers. In this study, models trained on external data alone do not reliably generalize to L2-ARCTIC. Among the tested configurations, balanced external-data training offers the most promising supervised setting. The pseudo-labeling experiments further indicate that confidence-based filtering alone is insufficient under domain mismatch. Overall, this study suggests that robust accent classification evaluation should simultaneously include speaker-disjoint evaluation and cross-corpus testing.
| Comments: | 9 pages, 1 figure, 7 tables. Presented at the 9th International Conference on Natural Language and Speech Processing (ICNLSP 2026), University of Trento, Trento, Italy, September 25-26, 2026. Proceedings to appear in the ACL Anthology |
| Subjects: | Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2610.13440 [eess.AS] |
| (or arXiv:2610.13440v1 [eess.AS] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13440 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Homayoon Beigi [view email]
[v1]
Fri, 9 Oct 2026 11:38:44 UTC (59 KB)
来源：arXiv cs.CL · arxiv.org