Unverified50% confidenceFactExact time
谷歌于2018年提出Tacotron 2作为现代情感语音合成的基础架构
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Related Claims
UnverifiedGoogle released a text-to-speech (TTS) model capable of controllable emotion.69% similarUnverified2018 年 Google 发布的 BERT 模型引入了双向上下文理解能力，显著提升了细粒度情感分类的准确率61% similarUnverifiedAI声工坊 supports two emotion control modes: natural language control mode and reference voice timbre emotion mode.59% similarUnverified情感语音合成系统通过对音调、语速、能量等声学特征向量的精细控制来实现情绪表达58% similarUnverified语音情感识别技术已能从语调、语速、停顿中识别细粒度情绪状态，准确率超过85%55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/492639API
curl https://kongchang.com/api/v1/knowledge/claims/492639MCP
get_claim(id=492639)