一种利用辅助词重音建模和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
浏览论文内容
中文总结 AI 辅助
本文提出一种结合辅助词重音建模与词跨度正则化的句子重音检测框架，在TinyStress-15K基准上取得最优性能。
中文摘要 AI 辅助
韵律重音是自动发音评估（APA）的一个关键方面，涵盖句子重音检测（SSD）和单词重音检测（WSD）。SSD突出显示塑造话语意义的语义显著词，而WSD识别每个单词内的主要重读音节以确保词汇清晰度。然而，大多数先前的工作将SSD和WSD视为独立任务，忽视了它们对音高、时长和强度等韵律线索的共同依赖。为解决这一差距，我们提出了一种有效的SSD方法，通过一种新颖的建模范式将SSD与辅助WSD相结合。此外，我们引入了一个词跨度重音正则化器（WSR），将token级别的SSD概率集中在每个重读单词跨度内。在TinyStress-15K基准上的实验表明，所提出的方法优于强基线，完整配置取得了最佳的SSD结果。
英文摘要
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.
发表机构
- National Taiwan Normal University（台湾师范大学）
机构由 AI 辅助整理，请以论文原文为准。
