基于constant q变换的音符起始点检测算法研究word格式论文.docxVIP

优秀毕业论文 精品参考文献资料 Abstract Note onset detection is the basic problem of music signal analysis and processing .It is the key of Content-Based Audio Information Retrieval ,especially for Query By Humming. The accuracy of the onset detection for each note affect the accuracy of Content-Based Audio Information Retrieval system in largely. Note onset detection techniques mostly learn speech end-point detection technology. Firstly, it introduces the research background and significance of note onset detection comprehensively, summarizes four steps of this detection system: pre-processing, feature extraction, selection feature equation, peak-picking. Secondly, it introduces several classical algorithms, and analyzes their advantages and disadvantages. Lastly, it puts forward a more effective ,new note detection algorithm—note onset detection based on Constant Q transform. On the basic of Constant Q Transform, using the spectral energy and sub-band spectral entropy to detect the note, calculation the distance of notes, last using hierarchical method to optimize the detection function. In audio signal processing, in order to observe the time position of the high frequency phenomenon, we should use the narrow time-domain window; In order to understand the low frequency phenomenon, we should use the wide time-domain window; Short time Fourier transform always use the same length of the window ,the Constant Q Transform is able to automatically adjust the window length. This paper is on basic of Constant Q Transform, it‘s spectral energy can reaction the changes well, but for the ―soft‖ notes of music signal, it‘s spectral energy don‘t have significantly changes, Spectral entropy is related to the randomness of the music signal, it is regardless of the amplitude of the signal, the ?soft‘ note‘s spectral entropy is not necessarily small, just to make up for the drawback of the method of spectral energy. Sub-band spectral entropy is not only inherited the advantages of spectral ent