Unverified70% confidenceBenchmarkExact time
Current state-of-the-art systems have achieved a WER below 5% on the standard English test set LibriSpeech.
2
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
8/28/2026
First Seen
Valid until: 11/26/2026
Sources
Related Entities
Related Claims
UnverifiedThe WER of top-tier ASR systems for English can be as low as below 5%.70% similarUnverified在 LibriSpeech 基准测试上顶尖系统 WER 已低于 2%，在 Switchboard 对话场景中通常为 5-8%，在多人会议场景（AMI、ICSI）中可能高达 15-25%68% similarUnverified当前主流 ASR 引擎的通用词错率（WER）已降至5%以下，但在医疗垂直领域的专有名词上错误率可能飙升至15%-30%，除非进行领域微调和自定义词典配置65% similarUnverifiedOnline A/B testing showed a 5% decrease in skip rate.64% similarUnverifiedAn early iteration scored five percentage points lower than the Huihui base model on the IFEval instruction-following benchmark.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/813858API
curl https://kongchang.com/api/v1/knowledge/claims/813858MCP
get_claim(id=813858)