ICA based informed source separation for digitally watermarked audio signals

R. Sharanya*, D. Sugumar, T. L. Sujithra, Susan Mary Bose, Divya Mary Koshy

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents an efficient, digital audio watermarking method based on one dimensional multilevel discrete wavelet transform(MDWT) and discrete cosine transform (DCT) for the application of copyright protection. The proposed scheme also employs informed source separation for the watermark extracted audio signal based on independent component analysis (ICA).In addition, the performance of the proposed algorithm in terms of Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR) and Normalized Root Mean Square Error (NRMSE) are also evaluated. The proposed scheme achieved good robustness against most of the attacks such as requantization, filtering, addition and multiplication of noise. The experimental result shows that the SNR value is about 36.12dB for the proposed algorithm, whereas by using only MDWT technique method gives only 30.2dB.

Original languageEnglish
Title of host publicationInformation Technology and Mobile Communication - International Conference, AIM 2011, Proceedings
Pages477-480
Number of pages4
DOIs
Publication statusPublished - 2011
EventInternational Conference on Information Technology and Mobile Communication, AIM 2011 - Nagpur, Maharashtra, India
Duration: 21-04-201122-04-2011

Publication series

NameCommunications in Computer and Information Science
Volume147 CCIS
ISSN (Print)1865-0929

Conference

ConferenceInternational Conference on Information Technology and Mobile Communication, AIM 2011
Country/TerritoryIndia
CityNagpur, Maharashtra
Period21-04-1122-04-11

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'ICA based informed source separation for digitally watermarked audio signals'. Together they form a unique fingerprint.

Cite this