Earticle

초록

영어

With the popularity of high fidelity and portable recording device, it becomes very easy for the attacker to spoof speaker verification system by voice playback. In this paper, it found that there exists obvious difference in the scale-factors, a parameter of MP3 codec, when the original and playback voices are compressed by MP3. So, a detection algorithm for the playback voice is proposed. The experimental results show that the detection accuracy of the proposed algorithm can reach to 99.51% for 4 different types of eavesdropping devices. Meanwhile, the algorithm is integrated into the speaker verification system based on GMM-UBM. The equal error rate (EER) of the system has dropped 32% and the system's ability to resist playback attack is improved.

목차

Abstract
 1. Introduction
 2. Mathematical Model of Voice Playback Attack
 3. Feature Extraction and Verification
  3.1. Feature Extraction
  3.2. Verification with PSDM
 4. Database Set
  4.1 Corpus Set
  4.2 Playback Speech Database set
 5. Experimental Results
  5.1 Influences of the Different Classifiers
  5.2 Influences of the Eavesdropping Devices' Coding Format
  5.3 Verification System with PSDM
 6. Conclusions
 References

키워드

저자

• U. Nanaji [ Department of Computer Science and Engineering, Vignan’s Institute of Information technology, AP, India ]
• N. Thirupathi Rao [ Department of Computer Science and Engineering, Vignan’s Institute of Information technology, AP, India ]
• Ch. Raj Kumar [ Department of Computer Science and Engineering, Vignan’s Institute of Information technology, AP, India ]
• Debnath Bhattacharyya [ Department of Computer Science and Engineering, Vignan’s Institute of Information technology, AP, India ]
• Hye-jin Kim [ Sungshin Women's University, Seoul, Korea ] corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Security and Its Applications

• 간기

  격월간

• pISSN

  1738-9976

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605