Key‐dependent audio fingerprinting technique based on a quantisation minimum‐distance hash extractor in the DWT domain

Abstract

A novel key-dependent audio fingerprinting technique is proposed by introducing the quantisation minimum distance (QMD) as a hash extractor in the discrete wavelet transform (DWT) domain. The quantiser dithers of the QMD are generated using a chaotic map whose initial value is used as a secret key for fingerprint extraction. Experimental results show that the proposed audio fingerprinting technique achieves with a small fingerprint size an excellent discrimination between audio signals of different contents and outperforms the existing Philips robust hash based techniques in terms of the robustness.

Audio Fingerprint Retrieval Method Based on Feature Dimension Reduction and Feature Combination

“…Sun et al [9] proposed an efficient audio fingerprint retrieval method based on subband spectral centroids, set seed segments to select subbands that need to extract features, extracts audio fingerprints based on subband spectral centroids, and set a hit count threshold during the retrieval phase, improved the recall rate and precision rate, but the query index time is longer. Terchi et al [10] proposed an audio fingerprint based on discrete wavelet transform, which extracts the audio fingerprint through multi-resolution decomposition of the discrete wavelet transform, which effectively improves the robustness of the audio fingerprint. Lin et al [11] proposed a feature extraction method based on spectral baseband phase, the spectral phase reconstruction is used to reduce the impact of the noise, which has better robustness under low SNR and poorer performance under noise.…”