GithubHelp home page GithubHelp logo

void-voice-liveness-detection's Introduction

void-voice-liveness-detection

Reproduction of paper Void: A Fast and Light Voice Liveness Detection System

任务描述

  • 受到2020 USENIX Security论文“Void: A fast and light voice liveness detection system”的启发,尝试复现文中描述的轻量化语音活体检测方法;
  • 任务 1:从语音样本中提取由4种子特征构成的Void语音特征向量;
  • 任务 2:训练合适的SVM分类器,用于准确区分真人语音和仿冒攻击语音;

数据集

  • 主要基于ASVspoof 2017 Version 2.0数据集;
  • 原文中为了验证Void系统的活体检测效果,作者还引入了自建重放攻击数据集以及隐藏语音、超声语音指令、合成语音等多种攻击方式;

代码功能简介

  • data_preparation.py
    • ASVspoof 2017 V2数据集的训练集、开发集和测试集的语音中分别提取Void特征并保存在features_labels路径下;
    • 特征提取相关函数在feature_extraction.py中定义;
  • train_svm.py
    • 特征提取完成后,使用训练集和开发集中的特征向量训练SVM分类器,训练好的模型保存在models路径下;
    • 根据原文中的实验结果,采用RBF核的SVM取得了最低的等错误率(EER=11.6%);
  • svm_evaluation.py
    • 用于单独验证一个已训练好的SVM分类器在测试集数据上的效果;

效果

  • 目前该项目在ASVspoof 2017 V2测试集上的等错误率与原文中的指标仍存在较大差距;
  • 该项目会持续改进,同时也欢迎大家针对特征提取过程和模型训练过程提出宝贵建议;

参考文献

void-voice-liveness-detection's People

Contributors

autoh avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

void-voice-liveness-detection's Issues

关于 High power frequency features 计算实现的一些问题

High power frequency features 包括四个部分,在您的代码中被表示为 N_peak, mu_peak and sigma_peak, P_est。
而 P_est 您的计算方法是,将 FV_LFP 的值作为 y,递增序列作为 x,拟合一个六阶多项式 f,然后使用将 np.arange(FV_LFP.size) 送入 f 得到输出,取前 32 个值。
但是原文中 P_est 是 f 的多项式系数。窃以为这里原文是自相矛盾的,六阶多项式系数应该只有 7 个,而可以看到原文的 Figure 7 中,P_est 的维度应该是 32,所以想了解您这样实现的依据?
相关的代码在项目根目录的 feature_extraction.py 文件中,函数 HighPowerFrequencyFeatures(FV_LFP, omega)
如果我的理解有误,还请海涵。

some discussions about reproducing Void

Dear Mr./Mrs.,

Nice work! I've also implemented the source code (Matlab version), and there exist gaps between those performances reported in the paper.

Hope you don't mind my getting in your touch. May I have your email for further contact? Mine is [email protected].

Best Regards.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.