Content-Based Authentication Using Digital Speech Data

Abstract

A watermarking technique for speech content and speaker authenticationscheme, which is based on using abstracts of speech features relevant to semanticmeaning and combined with an ID for the speaker is proposed in this paper. The IDwhich, represents the watermark for the speaker, is embedded using spread spectrumtechnique. While the extracted abstracts of speech features are used to represents thewatermark for the speech, is embedded in the original speech file using secret key.The abstracts speech feature is implemented using B-spline curve interpolation. Thepaper provides a background knowledge for the concept of speaker watermarkingand content-fragile watermarking based on digital speech data. Then, the suggestedfeature based authentication scheme is develop and the results from the evaluationare presented. It shows that the suggested scheme is successful for combiningspeech and speaker watermark authentication.