Audio fingerprinting is the process to obtain a compact content-based signature that summarizes the essence of an audio clip. In general, existing audio fingerprinting schemes based on wavelet transforms are not robust against large linear speed changes. The authors present a novel framework for content-based audio retrieval based on the audio fingerprinting scheme that is robust against large linear speed changes. In the proposed scheme, 8 levels Daubechies wavelet decomposition is adopted for extracting time-frequency features and two fingerprint extraction algorithms are designed. The experimental results from this study are discussed further into the article.
