Download Re-targeting Expressive Musical Style Using a Machine-Learning Method Expressive musical performing style involves more than what is simply represented on the score. Performers imprint their personal style on each performances based on their musical understanding. Expressive musical performing style makes the music come alive by shaping the music through continuous variation. It is observed that the musical style can be represented by appropriate numerical parameters, where most parameters are related to the dynamics. It is also observed that performers tends to perform music sections and motives of similar shape in similar ways, where music sections and motives can be identified by an automatic phrasing algorithm. An experiment is proposed for producing expressive music from raw quantized music files using machine-learning methods like Support Vector Machines. Experimental results show that it is possible to induce some of a performer’s style by using the music parameters extracted from the audio recordings of their real performance.
Download Finding Latent Sources in Recorded Music with a Shift-invariant HDP We present the Shift-Invariant Hierarchical Dirichlet Process (SIHDP), a nonparametric Bayesian model for modeling multiple songs in terms of a shared vocabulary of latent sound sources. The SIHDP is an extension of the Hierarchical Dirichlet Process (HDP) that explicitly models the times at which each latent component appears in each song. This extension allows us to model how sound sources evolve over time, which is critical to the human ability to recognize and interpret sounds. To make inference on large datasets possible, we develop an exact distributed Gibbs sampling algorithm to do posterior inference. We evaluate the SIHDP’s ability to model audio using a dataset of real popular music, and measure its ability to accurately find patterns in music using a set of synthesized drum loops. Ultimately, our model produces a rich representation of a set of songs consisting of a set of short sound sources and when they appear in each song.
Download Improving Polyphonic Melody Extraction By Dynamic Programming Based Dual F0 Tracking The suitability of optimal path finding methods for vocal melody extraction in polyphonic music is well recognized since they combine local pitch strength and temporal smoothness considerations in a global sense. However, when such single-F0 tracking systems are applied to sound mixtures in which pitched accompaniment is of comparable strength to the singing voice, they suffer from irrecoverable degradations. In this study we investigate the use of an optimal path finding method that is allowed to dynamically track multiple F0 paths, specifically two, through the F0 candidate space. It is shown that when such a system is applied to typical polyphonic mixtures with vocal solo the melodic information is indeed retrieved. Audio examples are available at http://www.ee.iitb.ac.in/daplab/DualF0TrackingResults_DAFx
Download Reservoir Computing: a powerful Framework for Nonlinear Audio Processing This paper proposes reservoir computing as a general framework for nonlinear audio processing. Reservoir computing is a novel approach to recurrent neural network training with the advantage of a very simple and linear learning algorithm. It can in theory approximate arbitrary nonlinear dynamical systems with arbitrary precision, has an inherent temporal processing capability and is therefore well suited for many nonlinear audio processing problems. Always when nonlinear relationships are present in the data and time information is crucial, reservoir computing can be applied. Examples from three application areas are presented: nonlinear system identification of a tube amplifier emulator algorithm, nonlinear audio prediction, as necessary in a wireless transmission of audio where dropouts may occur, and automatic melody transcription out of a polyphonic audio stream, as one example from the big field of music information retrieval. Reservoir computing was able to outperform state-of-the-art alternative models in all studied tasks.
Download Beat-Marker Location using a Probabilistic Framework and Linear Discriminant Analysis This paper deals with the problem of beat-tracking in an audiofile. Considering time-variable tempo and meter estimation as input, we study two beat-tracking approaches. The first one is based on an adaptation of a method used in speech processing for locating the Glottal Closure Instants. The results obtained with this first approach allow us to derive a set of requirements for a robust approach. This second approach is based on a probabilistic framework. In this approach the beat-tracking problem is formulated as an “inverse” Viterbi decoding problem in which we decode times over beat-numbers according to observation and transition probabilities. A beat-template is used to derive the observation probabilities from the signal. For this task, we propose the use of a machine-learning method, the Linear Discriminant Analysis, to estimate the most discriminative beat-template. We finally propose a set of measures to evaluate the performances of a beattracking algorithm and perform a large-scale evaluation of the two approaches on four different test-sets.