Unverified50% confidenceFactExact time
STT models in low signal-to-noise ratio scenarios do not admit that they cannot hear clearly; instead, they tend to fabricate plausible but incorrect words and phrases (producing hallucinations)
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTraditional speech-to-text (STT) technology relies on Hidden Markov Models and Gaussian Mixture Models.73% similarUnverified流式STT在用户说话过程中就持续输出部分识别结果，而批量模式需等待完整音频才能开始处理70% similarUnverifiedResearch shows that Whisper's probability of hallucination is particularly prominent during silent segments, producing fluent transcription results whose content does not match the original audio.67% similarUnverified编解码器模拟能覆盖可预测、可参数化的信道层面失真，但无法解决背景噪声组合、自然语音重叠和情绪化声学偏移66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928094API
curl https://kongchang.com/api/v1/knowledge/claims/928094MCP
get_claim(id=928094)