tailieunhanh - Mpeg 7 audio and beyond audio content indexing and retrieval phần 3

Khác được thành lập ở mức độ thấp mô tả ngoài MPEG-7 được giới thiệu. Để giúp người đọc hình dung ra các loại thông tin mà những mô tả truyền đạt một số kết quả thử nghiệm được đưa ra để minh họa các định nghĩa. | 42 2 LOW-LEVEL DESCRIPTORS where Env l is the signal envelope defined in Equation . The multiplying factor Nhop Fs is the frame sampling rate. This enables the conversion from the discrete frame index domain to the continuous time domain. The unit of the TC feature is the second. Figure illustrates the extraction of the TC from a dog bark sound. Spectral Timbral Requirements The spectral timbral features aim at describing the structure of harmonic spectra. Contrary to the previous spectral descriptors the basic spectral descriptors of Section they are extracted in a linear frequency space. They are designed to be computed using signal frames if instantaneous values are required or larger analysis windows if global values are required. In the case of a frame-based analysis the following parameters are recommended by the standard Frame size Lw 30 ms. Hop size hopSize 10ms. If global spectral timbral features are extracted from large signal segments the size of the analysis window should be a whole number of the local fundamental period. In that case the recommended parameters are Frame size Lw 8 fundamental periods. Hop size hopSize 4 fundamental periods. In both cases the recommended windowing function is the Hamming window. The extraction of the spectral timbral descriptors requires the estimation of the fundamental frequency f0 and the detection of the harmonic components of the signal. How these pre-required features should be extracted is again not part of the MPEG-7 standard. The following just provides some general definitions along with indications of the classical estimation methods. The schema of a pitch and harmonic peak detection algorithm is shown in Figure . This detection algorithm consists of four main steps 1. The first step is to extract by means of an FFT algorithm the spectrum S k of the windowed signal defined in Equation . The amplitude spectrum S k is then computed. 2. Estimation of the pitch frequency f0 is then .