Expired50% confidenceFactExact time
XiaoWu uses a local LLM as a post-processing layer to proofread and refine the speech recognition output.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
XiaoWu Voice Input Method: Powered by Local LLMs for Accurate Offline Speech Recognition
bilibilii-xiaowu6/23/2026
Related Claims
UnverifiedXiaoWu is a voice input method based on a local large language model that supports fully offline operation.76% similarUnverified语音编码器 + LLM 解码器的组合是 2023 年以来语音大模型的主流范式，Qwen-Audio、Gemini Audio、Phi-4-audio 等均采用类似设计68% similarVerifiedSpeech recognition technology has evolved from hidden Markov models (HMMs) to recurrent neural networks (RNNs) and then to end-to-end models.67% similarUnverifiedThe transcription and summarization capability of AI voice recorders is essentially the product of deploying speech recognition (ASR) technology and large language models (LLM) in series.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41194API
curl https://kongchang.com/api/v1/knowledge/claims/41194MCP
get_claim(id=41194)