arXiv：cs.CL· Tien-Hong Lo, Fong-Chun Tsai, Ting-An Hung, Yu-Hsuan Hsieh, Yao-Ting Sung, Berlin Chen·· 6 小时前AI 评分27
结合辅助词重音建模与损失优化的新型句子重音检测框架
A Novel Sentence Stress Detection Framework Leveraging Auxiliary Word-Stress Modeling and Loss Optimization
AI 导读
研究提出一种将句子重音检测（SSD）与辅助词重音检测（WSD）结合的新建模范式，并引入词跨度重音正则化器（WSR），将 token 级 SSD 概率集中到重音词跨度内。在 TinyStress-15K 基准上，该方法优于强基线，完整配置取得最佳 SSD 结果。
正文
Abstract:Prosodic stress is a crucial aspect of automatic pronunciation assessment (APA), encompassing both sentence stress detection (SSD) and word stress detection (WSD). SSD highlights semantically salient words that shape discourse meaning, while WSD identifies the primary stressed syllable within each word to ensure lexical clarity. However, most prior work treats SSD and WSD as independent tasks, overlooking their shared reliance on prosodic cues such as pitch, duration, and intensity. To address this gap, we propose an effective SSD approach combining SSD with auxiliary WSD via a novel modeling paradigm. In addition, we introduce a word-span stress regularizer (WSR) that concentrates token-level SSD probabilities within each stressed word span. Experiments on the TinyStress-15K benchmark show that the proposed method outperforms strong baselines, with the complete configuration achieving the best SSD result.
| Comments: | Interspeech 2026 |
| Subjects: | Audio and Speech Processing (eess.AS); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.07626 [eess.AS] |
| (or arXiv:2610.07626v1 [eess.AS] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07626 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tien-Hong Lo [view email]
[v1]
Tue, 6 Oct 2026 02:18:10 UTC (238 KB)
来源：arXiv：cs.CL · arxiv.org