Unverified50% confidenceBenchmarkExact time
Marimba's personal information detection achieves an entry-level F1 of 0.904 on synthetic Brazilian Portuguese speech and 1.000 on human reference transcripts.
1
Sources
50%
Confidence
Long-term
Relevance
11/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMarimba achieves decoder AUROC of 0.80–0.92 on a private conversation test set and 0.92–0.97 on public read speech.70% similarUnverifiedAudio fingerprint analysis is a technology that identifies or compares tracks by extracting acoustic features from audio signals, and Shazam's song recognition and rights holders' Content ID systems are both based on it.53% similarUnverifiedMedAstra's pure speech retriever achieves 87.6 Recall@10, the hybrid configuration achieves 90.4, and transcription-first dense retrieval achieves 81.0.53% similarUnverifiedShazam通常需要至少5到10秒的清晰音频才能生成可靠的声纹指纹并完成数据库匹配52% similarUnverifiedQwen-Audio-Jev achieves an equal error rate (EER) of 6.50% on the VoxCeleb1-O speaker verification benchmark.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1173845API
curl https://kongchang.com/api/v1/knowledge/claims/1173845MCP
get_claim(id=1173845)