Abstract:In this paper, we propose a method called temporal correlation support vector machine (TCSVM) for automatic major-minor chord recognition in audio music. We first use robust principal component analysis to separate the singing voice from the music to reduce the influence of the singing voice and consider the temporal correlations of the chord features. Using robust principal component analysis, we expect the low-rank component of the spectrogram matrix to contain the musical accompaniment and the sparse component to contain the vocal signals. Then, we extract a new logarithmic pitch class profile (LPCP) feature called enhanced LPCP from the low-rank part. To exploit the temporal correlation among the LPCP features of chords, we propose an improved support vector machine algorithm called TCSVM. We perform this study using the MIREX'09 (Music Information Retrieval Evaluation eXchange) Audio Chord Estimation dataset. Furthermore, we conduct comprehensive experiments using different pitch class profile feature vectors to examine the performance of TCSVM. The results of our method are comparable to the state-of-the-art methods that entered the MIREX in 2013 and 2014 for the MIREX'09 Audio Chord Estimation task dataset.

In this paper, a machine-learning approach called Sparse Representation-based Classification (SRC)

Truncation is an efficient way to measure attenuation spectrum of PMMA and PS, and we set up the systems measuring the attenuation of POF. The position of low loss can be discovered, therefore we not only can choose suitable transmission windows and suitable pump sources, but also use wavelength division multiplexing (WDM) to settle bandwidth problem. We analyze the attenuation spectrum and make a comparison between PMMA and PS fiber. Three windows of PMMA are 520nm, 574nm and 650nm. The window at 650nm is usually used. The loss at 520nm, 574nm is smaller and the attenuation spectrum is flatter, so this window will be used better. PS fiber has been found existing six windows. There are 550 nm, 580 nm,630 nm,670 nm,733 nm and 780nm in the range of measurement. Two windows of 550nm and 580nm are suitable for exploring.

No abstract