DMCA
AUDIO SIGNATURE EXTRACTION BASED ON PROJECTIONS OF SPECTROGRAMS
| Citations: | 2 - 0 self |
BibTeX
@MISC{Radhakrishnan_audiosignature,
author = {Regunathan Radhakrishnan and Claus Bauer and Corey Cheng and Kent Terry},
title = {AUDIO SIGNATURE EXTRACTION BASED ON PROJECTIONS OF SPECTROGRAMS},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Content-based signatures are designed to be a robust bit-stream representation of the content so as to enable content identi¿cation even though the original content may go through various signal processing operations. In this paper, we pro-pose a novel content-based audio signature extraction method that captures temporal evolution of the audio spectrum. The proposed method, ¿rst, divides the input audio into overlap-ping chunks and computes a spectrogram for each chunk. Then, it projects each of the spectrograms onto random ba-sis vectors to create a signature that is a low-dimensional bit-stream representation of the corresponding spectrogram. Our experimental results show the robustness and sensitivity of the proposed content-based audio signature extraction method for various signal processing operations on audio content. 1.
Keyphrases
various signal processing operation content-based audio signature extraction method overlap-ping chunk audio content content identi cation corresponding spectrogram robust bit-stream representation audio spectrum content-based signature original content temporal evolution random ba-sis vector experimental result low-dimensional bit-stream representation
