A Recording Device Identification Algorithm Based on Improved PNCC Feature and Two-Step Discriminative Training

HE Qian-hua; WANG Zhi-feng; Alexander I Rudnicky; ZHU Zheng-yu; LI Xin-chao

doi:10.3969/j.issn.0372-2112.2014.01.031

您当前的位置：

首页 >

文章列表页 >

A Recording Device Identification Algorithm Based on Improved PNCC Feature and Two-Step Discriminative Training

更新时间：2025-07-16

- A Recording Device Identification Algorithm Based on Improved PNCC Feature and Two-Step Discriminative Training
- Acta Electronica Sinica Vol. 42, Issue 1, Pages: 191-198(2014)
- 作者机构：
  
  1. 华南理工大学电子与信息学院,广东,广州,510640
  2. 卡内基梅隆大学计算机学院,匹兹堡,美国,15213
  3. 华南理工大学电子与信息学院,广东,广州,510640
  4. 卡内基梅隆大学计算机学院,匹兹堡,美国,15213
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2014.01.031
  CLC： TN912.3
- Published：2014
- 稿件说明：
移动端阅览
HE Qian-hua, WANG Zhi-feng, Alexander I Rudnicky, et al. A Recording Device Identification Algorithm Based on Improved PNCC Feature and Two-Step Discriminative Training[J]. Acta Electronica Sinica, 2014, 42(1): 191-198.
DOI：

HE Qian-hua, WANG Zhi-feng, Alexander I Rudnicky, et al. A Recording Device Identification Algorithm Based on Improved PNCC Feature and Two-Step Discriminative Training[J]. Acta Electronica Sinica, 2014, 42(1): 191-198. DOI： 10.3969/j.issn.0372-2112.2014.01.031.

摘要

录音设备来源识别是通过分析已获取的数字语音信号从而确定其录制设备的一种技术，属于数字音频盲取证.本文提出了一种基于改进PNCC特征和两步区分性训练的录音设备识别方法，由于音频中的静音包含了完整的设备信息，且不受说话人和文本等因素的影响，因此从静音段提取改进的PNCC特征，利用了PNCC的长时帧分析去除背景噪声对设备信息的影响.在模型方面，以GMM-UBM为基准模型，并通过两步区分性训练调整集内设备模型和通用背景模型，提升模型区分能力.该方法对于30种设备闭集识别的平均正确识别率为90.23%；对于15个集内和15个集外设备的测试，等错误率为15.17%，集内平均正确识别率为96.65%，验证了本文算法的有效性.

Abstract

Recording device identification is a kind of blind digital audio forensic technique

which extracts digital evidence of device mechanism involved in the generation of the speech recording by analyzing the acoustic signal.This paper proposes a recording device identification algorithm which is based on improved PNCC feature and two-step discriminative training.Due to the fact that silence periods contain the device information and is not affected by speaker and texture factors

this paper extracts improved PNCC from silence periods

which uses long term analysis to remove the effect of background noise.GMM-UBM is set as the baseline system

which is improved by two steps discriminative training.The experimental result indicates that the average accuracy of recording device identification on 30 devices is 90.23%;for 15 inset and 15 outset devices testing

the EER is 15.17% and ACC is 96.65%

which proves the effectiveness of the proposed algorithm.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Maximum F1-Score Criterion Based Discriminative Feature Compensation Training Algorithm for Automatic Mispronunciation Detection

A Discriminative Segmental Feature Transform Method Based on Uncorrelated Matching Pursuit

Related Author

HUANG Hao

XU Hai-hua

WANG Xian-hui

Wushour Silamu

斯拉木

CHEN Bin

NIU Tong

ZHANG Lian-hai

Related Institution

School of Information Science and Engineering, Xinjiang University

Temasek Laboratories, Nanyang Technological University

School of Information Science and Engineering Xinjiang University Urumqi Xinjiang China

Temasek Laboratories Nanyang Technological University Singapore

Institute of Information System Engineering, Information Engineering University

⁰