Mobile phone identification from speech recordings using Weighted Support Vector Machine

Yuechi Jiang, Hung Fat Frank Leung

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

13 Citations (Scopus)


In this paper, we propose a mobile phone identifier called Weighted Support Vector Machine with Weighted Majority Voting (WSVM-WMV) for a closed-set mobile phone identification task. The proposed WSVM-WMV can be regarded as a generalization of the traditional SVM identifier. On using Mel-frequency Cepstral Coefficients (MFCC) and Linear-frequency Cepstral Coefficients (LFCC) as the feature vectors, the proposed identifier can improve the identification accuracy from 92.42% to 97.86% and from 90.44% to 98.33% respectively, as compared with the traditional SVM identifier in identifying a set of 21 mobile phones.
Original languageEnglish
Title of host publicationProceedings of the IECON 2016 - 42nd Annual Conference of the Industrial Electronics Society
PublisherIEEE Computer Society
Number of pages6
ISBN (Electronic)9781509034741
Publication statusPublished - 21 Dec 2016
Event42nd Conference of the Industrial Electronics Society, IECON 2016 - Palazzo dei Congressi, Florence, Italy
Duration: 24 Oct 201627 Oct 2016


Conference42nd Conference of the Industrial Electronics Society, IECON 2016


  • Audio forensics
  • Mobile phone identification
  • Weighted Majority Voting
  • Weighted Support Vector Machine

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this