umitkacar /ensemble-speaker-verification
合奏扬声器验证达到97%准确率——MFCC+DTW(92%)和Resemblyzer CNN(94%)的智能融合用于语音认证
Jupyter Notebook5
voice-forensics 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
合奏扬声器验证达到97%准确率——MFCC+DTW(92%)和Resemblyzer CNN(94%)的智能融合用于语音认证
VoicePrint: Forensic speaker attribution for AI voice blends. Match synthetic clones to source voices via speaker embeddings & cosine similarity. Open-source Python research toolbox.
🎙️ VoxTrace — AI Trust & Digital Media Evidence Infrastructure for synthetic voice detection, audio tamper analysis, and cryptographic provenance.