English(EN) Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation

新型DSSM-CRF模型提升对话语音情感识别能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

研究人员开发了一种名为DSSM-CRF的新型双尺度状态空间模型，用于对话中的语音情感识别。该模型通过使用双向状态空间模型在帧和对话尺度上编码语音表示，将跨说话人上下文影响与说话人内部情感演变分离开来。然后，系统为每个说话人采用动态条件随机场链，从而能够根据上下文相关的话语预测情感转换。DSSM-CRF在基准数据集上表现强劲，在IEMOCAP上实现了75.81%的UA和74.90%的WA，在MELD上实现了54.72%的WA和49.31%的WF1。 AI

影响该模型可以提高AI系统在对话环境中理解和响应人类情感的准确性。

排序理由这是一篇详细介绍新型语音情感识别模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 32 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新型语音情感识别模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Guan-Hua Wen, Hou-Chiang Tseng, Kuan-Yu Chen · 2026-09-07 04:00

面向对话语音情感识别的双尺度状态空间模型与说话人感知动态CRF

arXiv:2608.22399v2 Announce Type: replace Abstract: Conversational speech emotion recognition must reconcile acoustic evidence across temporal scales with two interaction processes: cross-speaker contextual influence and within-speaker emotion evolution. We propose DSSM-CRF, an a…

本文如何被排名

报道来源 [1]

面向对话语音情感识别的双尺度状态空间模型与说话人感知动态CRF

相关实体

相关话题