Unverified50% confidenceFactExact time
Google Speech-to-Text和讯飞等传统ASR服务需要将语音数据上传至远程服务器处理
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
XiaoWu Voice Input Method: Powered by Local LLMs for Accurate Offline Speech Recognition
bilibilii-xiaowu6/23/2026
Related Claims
Unverified传统语音助手如Amazon Alexa和Google Assistant的本地设备通常只负责唤醒词检测和音频采集，ASR、NLU和TTS都在远端服务器完成71% similarUnverified主流ASR系统(如Whisper、Google Speech-to-Text)主要在成人语音数据集上训练，在儿童语音上的词错误率通常比成人高出30%-50%70% similarUnverifiedAudio data in WeChat Mini Programs can be transmitted to backend speech recognition services via WebSocket or HTTP requests.69% similarUnverified目前主流AI语音交互方案——无论开源项目还是商业产品——基本都依赖WebSocket作为语音数据和信令的传输通道69% similarUnverifiedGoogle 的 AudioPaLM 是直接实现音频到音频映射的端到端语音模型69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41188API
curl https://kongchang.com/api/v1/knowledge/claims/41188MCP
get_claim(id=41188)