PulseAugur
中
实时 05:36:01
English(EN) EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis

新的TTS系统EmoTra-TTS模仿语音中自然的情感过渡

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了EmoTra-TTS，一个新颖的文本到语音系统，旨在模仿单一句子中情感的自然、连续演变。与使用静态情感标签的现有系统不同，EmoTra-TTS采用多通道流混合流水线和双阶段效价-唤醒度-优势度（Valence-Arousal-Dominance）条件控制，以实现精确、可控的句内情感过渡。据报道，这种方法将情感过渡质量提高了87%，并在与最先进和商业系统相比的用户偏好测试中显示出显著的胜率，同时模型参数增加极少且没有延迟开销。 AI

影响 增强了语音合成的自然性和表现力，可能改善人机交互和可访问性。

排序理由 详细介绍新模型/方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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

新的TTS系统EmoTra-TTS模仿语音中自然的情感过渡

本文如何被排名

Signal score
43 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍新模型/方法的学术论文。[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]

  1. arXiv cs.AI TIER_1 English(EN) · Tianchi Liu, Zeyang Song, Tianrui Wang, Zhipeng Li, Chenglin Xu, Yiwen Guo ·

    EmoTra-TTS：用于语音合成的流畅句内情感转换

    arXiv:2608.23791v1 Announce Type: cross Abstract: Psychological research on emotion dynamics has established that human affect is a continuous, evolving process: emotions rise, decay, and transition within seconds. Current emotional text-to-speech (TTS) systems, however, conditio…

相关实体

相关话题