arXiv：cs.CL· Pol Buitrago, Oriol Pareras, Federico Costa, Javier Hernando·· 6 小时前AI 评分33
用跨语言迁移矩阵量化副语言语音任务中的语言依赖
Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks
AI 导读
研究提出跨语言迁移矩阵（CLTM），用于系统量化给定任务内语言对之间的跨语言交互。基于多语言 HuBERT 编码器，将其应用于性别识别和说话人验证两项副语言任务，分析微调时供体语言数据如何影响目标语言表现。结果显示不同任务与语言间存在明显不同的迁移模式，反映出系统性的语言依赖效应。
正文
Abstract:Paralinguistic speech tasks are often considered relatively language-agnostic, as they rely on extralinguistic acoustic cues rather than lexical content. However, prior studies report performance degradation under cross-lingual conditions, indicating non-negligible language dependence. Still, these studies typically focus on isolated language pairs or task-specific settings, limiting comparability and preventing a systematic assessment of task-level language dependence.
We introduce the Cross-Lingual Transfer Matrix (CLTM), a systematic method to quantify cross-lingual interactions between pairs of languages within a given task. We apply the CLTM to two paralinguistic tasks, gender identification and speaker verification, using a multilingual HuBERT-based encoder, to analyze how donor-language data affects target-language performance during fine-tuning. Our results reveal distinct transfer patterns across tasks and languages, reflecting systematic, language-dependent effects.
| Comments: | 6 pages, 5 figures, Published in Interspeech 2026 |
| Subjects: | Audio and Speech Processing (eess.AS); Computation and Language (cs.CL) |
| Cite as: | arXiv:2603.08231 [eess.AS] |
| (or arXiv:2603.08231v2 [eess.AS] for this version) | |
| https://doi.org/10.48550/arXiv.2603.08231 arXiv-issued DOI via DataCite |
|
| Journal reference: | Proceedings of Interspeech 2026, pp. 2297--2302 |
| Related DOI: | https://doi.org/10.21437/Interspeech.2026-2745
DOI(s) linking to related resources |
Submission history
From: Pol Buitrago [view email]
[v1]
Mon, 9 Mar 2026 11:02:57 UTC (2,617 KB)
[v2]
Tue, 6 Oct 2026 13:43:11 UTC (2,552 KB)
来源：arXiv：cs.CL · arxiv.org