小波轉換應用於音訊特徵萃取之研究

Feature Extraction Using Wavelet Transformation for Audio Fingerprinting

王行之(Hsing-Chih Wang)

指導教授 ： 謝尚琳

大同大學/電機資訊學院/資訊工程學系所/碩士(2005年)

摘要

本篇論文提出一種創新的音訊指紋特徵抽取方法，於小波頻率域上進行特徵值抽取。在研究中我們嘗試縮減可供辨識所需的最短音訊長度(粒度)用以增加音訊指紋系統的彈性以應付各樣需求，並且滿足了音訊指紋系統中強健性與可靠性的要求。根據實驗結果，依所提方法抽取出的特徵值同時俱有強健性與可靠性，並能抵抗多種的信號衰減與壓縮。此外，辨識所需的最短音訊長度也低於前人之研究。

關鍵字

特徵萃取 ； 小波轉換

並列摘要

An innovated feature extraction algorithm by using discrete wavelet transform (DWT) for audio fingerprinting was proposed in this study. In this study, we attempt to reduce minimal length of audio needed for identification (i.e. granularity) for increasing flexibility in dealing with various requirements of an audio fingerprinting system. Moreover, both the robustness and reliability issues of fingerprinting system are addressed. The experimental results show that the proposed method is not only reliable but also robust against various signal degradations. Furthermore, the granularity of fingerprint is smaller than previous work.

並列關鍵字

audio fingerprinting ； Wavelet Transformation

參考文獻

[3] L. Gomes, P. Cano, E. Gómez, M. Bonnet and E. Batlle, “Audio Watermarking and Fingerprinting: For Which Applications?”

[4] J. Haitsma, T. Kalker, “A Highly Robust Audio Fingerprinting System”, In Proc. ISMIR’02, 2002.

[5] J. Haitsma, T. Kalker, “Speed-change resistant audio fingerprinting using auto-correlation”, IEEE International Conference on Acoustics, Speech, and Signal Processing, (ICASSP '03), Volume 4, pp. IV - 728-31, Apr. 2003.

[8] R. Lancini, F. Mapelli and R. Pezzano, “Audio Content Identification by using Perceptual Hashing ”, IEEE International Conference on Multimedia and Expo, 2004.

[9] C. S. Lu, “Audio Fingerprinting based on Analyzing Time-Frequency Localization of Signals”, IEEE Workshop on Multimedia Signal Processing, pp. 174 – 177, Dec. 2002.