In this paper, a system for automatic classification of musical instrument sounds is introduced. As features mel-frequency cepstral coefficients and as classifiers probabilistic neural networks are used. The experimental dataset included 4548 solo tones from 19 instruments of MIS database (The University of Iowa Musical Instrument Samples). Experiments for different system structures (hierarchi...

The META-EVI is a novel interface created from an extensive augmentation of the Steiner MIDI EVI, a brass style ‘electric valve instrument’ (EVI), which was expanded with 11 analog sensors and 10 digital switches. The main goal of this project consists in achieving a performance tool that exhibits truly innovative levels of musical expression much beyond what is possible with the original instr...

This paper deals with the effects of integrated vibrotactile feedback on the“feel”of a digital musical instrument. Building on previous work developing a DMI with integrated vibrotactile feedback actuators, we discuss how to produce instrument-like vibrations, compare these simulated vibrations with those produced by an acoustic instrument and examine how the integration of this feedback effect...

This paper proposes a new musical instrument estimation of polyphony using autocorrelation functions. We notice that each musical instrument has each autocorrelation function. Polyphony can be separated into each monophony using comb filters ( ). We can obtain the autocorrelation functions for the outputs of comb filters from the autocorrelation functions of the monophony. By the pattern patchi...

MidiGrid is a computer-based musical instrument, primarily controlled with the computer mouse, which allows live performance of MIDI-based musical material by mapping 2dimensional position onto musical events. Since its invention in 1987, it has gained a small, but enthusiastic, band of users, and has become the primary instrument for several people with physical disabilities. This paper review...

In this paper we consider the problem of modeling spectro-temporal behaviour of musical sounds, with applications for musical instrument recognition. Using instanteneous sound features, such as cepstral envelopes and cepstral derivatives, the temporal evolution of the sound is transcribed into a new representation as a sequence of spectral features. Applying information-theoretic sequence match...

The ability of a listener to recognize sound sources, and in particular musical instruments from the sounds they produce, raises the question of determining the acoustical information used to achieve such a task. It is now well known that the shapes of the temporal and spectral envelopes are crucial to the recognition of a musical instrument. More recently, Modulation Power Spectra (MPS) have b...

The task of identifying musical instruments in an audio recording is a difficult problem. While there exists a body of literature on single instrument identification, little research has been performed on the more complex, but real-world, situation of more than one instrument present in the signal. This work proposes a Bayesian method for multi-label classification of musical instrument timbre....

The Squeezables is a computer music instrument that allows a group of players to perform and improvise musical compositions by using a set of squeezing and pulling gestures. The instrument, comprised of six squeezable and retractable gel balls mounted on a small podium, addresses a number of hardware and software challenges in electronic music interface design. It is designed to provide an alte...

Drawing on concepts from systemics, cybernetics, and musical automata, this paper proposes a mechatronic, electroacoustic instrument that allows for shared control between programmed, mechanized motion and a human interactor. We suggest that such an instrument, situated somewhere between a robotic musical instrument and a passive controller, will foster the emergence of new, complex, and meanin...