A novel framework for music tagging is proposed. First, each music recording is represented by bio-inspired auditory temporal modulations. Then, a multilinear subspace learning algorithm based on sparse label coding is developed to effectively harness the multi-label information for dimensionality reduction. The proposed algorithm is referred to as Sparse Multi-label Linear Embedding Nonnegativ...

By Hermitian mapping, we suggest unitary cyclic root-MUSIC algorithm to exploit the signal selective property of cyclostationary signals in this paper. To deal with correlated or coherent case, we design the forward backward cyclic autocorrelation matrix, without conjugate centrosymmetric array configurations. Compared with unitary root-MUSIC algorithm, the proposed method has a better performa...

We present a system that automatically turns the pages of the music score for musicians during a performance. It is based on a new algorithm for following an incoming audio stream in real time and aligning it to a music score (in the form of a synthesized audio file). Precision and robustness of the algorithm are quantified in systematic experiments, and a demonstration using an actual page tur...

This paper presents an effective antenna array based on MUSIC algorithm for two-dimensional direction-of-arrival estimation of multiple narrow-band sources impinging on the far field of the antenna array. Compared with the previous work, the proposed array can improve the performance of MUSIC algorithm, such as it can resolve the incoming rays with very close azimuth angles or very close elevat...

One effective approach to music analysis/synthesis is multiple wavetable interpolation, which matches an audio signal at selected breakpoints by determining weightings for several wavetables; the sound is resynthesized using multiple wavetable additive synthesis by interpolating between the weightings for each wavetable at consecutive breakpoints. This article presents a new breakpoint-matching...

We describe the creation of a new domain for the Methodius Natural Language Generation System, and an evaluation of Methodius’ parameterized comparison generation algorithm. The new domain was based around music and performers, and texts about the domain were generated using Methodius. Our evaluation showed that test subjects learned more from texts that contained comparisons than from those th...

| Most receiver designs for asynchronous Direct-Sequence Code-Division Multiple-Access systems exploit timing information to simultaneously detect the desired signal and suppress the interference. In this paper, a previously proposed MUSIC delay estimation algorithm is considered which requires no initial information and no exhaustive search of the delays. Based on a Taylor series expansion, ap...

An estimation method of source location of undesired electromagnetic wave from electronic devices by using the MUSIC algorithm is proposed. The MUSIC algorithm can estimate the direction of arrival accurately, however, the estimation error is large in the case of short range multiple coherent sources. In order to overcome this problem, a method to improve the estimation accuracy is presented. E...

The trends of miniaturization and increasing storage capabilities for portable music players made it possible to carry increasingly more music on small portable devices, but it also introduced negative consequences for the user interface and navigation. Finding music in large collections can be hard if one does not know exactly what to look for. In this paper a novel user interface to browse an...

In this paper, an autonomous intelligent music composition tool was developed using Genetic Algorithms. The research has been structured into two phases, each of which builds upon the previous one. The first phase of the project was to develop more sophisticated fitness measures for the genetic algorithm, with the goal of applying data compression techniques to identify musically sound patterns...