Unverified60% confidenceFactExact time
The introduction of deep neural networks in 2012 caused speech recognition error rates to drop by more than 30%.
2
Sources
60%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedThe latest version of pyannote.audio adopts an end-to-end neural network architecture (EEND), and the diarization error rate (DER) on standard evaluation sets has dropped below 10%.73% similarUnverified有研究表明在自发语音场景下WER从5%提升到8%，用户感知的任务完成率可能下降超过30%69% similarUnverifiedThe addition of fixed acoustic features slightly reduces the proportion of the 512d semantic component after normalization, harming audio-to-audio tasks that need to ignore speaker timbre: spoken topic classification (SIBFLEURS) drops from 57.2% to 21.3%, and spoken intent (MInDS14) drops from 97.6% to 88.3%.67% similarUnverified现代语音识别技术基于深度学习中的端到端神经网络架构，尤其是Transformer模型的引入使识别准确率大幅提升66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/521177API
curl https://kongchang.com/api/v1/knowledge/claims/521177MCP
get_claim(id=521177)