INTER:D: a drum sound equalizer for controlling volume and timbre of drums

Abstract

A drum sound equalizer, called INTER:D, is described that enables a listener to control the volume and timbre of bass and snare drum sounds in commercial compact-disc recordings. Although the characteristics of the drum sounds are often closely related to the impression made by a musical piece, conventional graphic equalizers cannot adjust their characteristics because they have volume sliders only for the frequency bands. INTER:D provides drum-specific volume sliders that directly control the frequency components of drum sounds, enabling a listener to intuitively cut or boost the volume of each drum. In addition, INTER:D enables a listener to replace the original timbre of each drum with another timbre selected from a dropdown list. These interactive functions are achieved using an automatic music content analysis system based on low-level audio signal processing. This system can estimate the power spectrogram of each drum sound and detect the onset times in a musical piece. Subjective experiments showed that INTER:D can add a new dimension to the way users experience music.

Upmixing from mono - A source separation approach

“…This is necessary for upmixing in order to allow the placement of percussion sources at points in the stereo field. Again, a number of techniques used here are based on non-negative matrix and tensor factorisations [9,10,11], while others use template matching and adaptation [12,13]. Other techniques make use of simple heuristics based on characteristics of both pitched and harmonic instruments [14,15].…”

Transcription and Separation of Drum Signals From Polyphonic Music

“…Other unsupervised methods use psychoacoustic criteria to group related partials [40] or aim to compactly describe the spectrogram as a sum of a few components by means of methods such as ISA [41], NMF [42], or Sparse Coding [43]. Furthermore, several solutions to the specific problem of drum track extraction or resynthesis from polyphonic music have already been proposed (see, for example, [11], [15], and [44]). …”

Integration and Adaptation of Harmonic and Inharmonic Models for Separating Polyphonic Musical Signals

“…Our goal is to build an instrument equalizer, INTER [1], that enables a user to remix multiple audio tracks corresponding to different instruments in compact-disc (CD) recordings by changing the volume of each track. While most previous equalizers, such as graphic equalizers and tone controls for bass and treble, change the volume of each frequency band to adjust frequency characteristics, INTER can change the volume of each instrument to adjust the mixing balance of instruments in CD recordings.…”

“…While most previous equalizers, such as graphic equalizers and tone controls for bass and treble, change the volume of each frequency band to adjust frequency characteristics, INTER can change the volume of each instrument to adjust the mixing balance of instruments in CD recordings. Because it was dif cult to extract (i.e., demix) tracks from CD recordings, however, the proposed INTER was partially achieved only for drums: a drum-sound equalizer, called INTER:D [1], that changes the volume of drum sounds (inharmonic sounds). We therefore aim to built fully functional IN-TER, i.e., to build an advanced instrument equalizer for more general sound mixtures, including both harmonic and inharmonic sounds.…”

“…To solve this over-training problem, we estimated the model parameters by using their prior information and initial values that are given on the basis of multiple tracks in the standard MIDI le (SMF) corresponding to the target piece. 1 Moreover, we used several original constraints based on the Kullback-Leibler (KL) divergence. For example, if the inharmonic-structure tone model captures harmonic components of a sound, it is penalized.…”