• Corpus ID: 34784995

Computational Modelling of Perceptual Music Features View project Normative Computational Theory of Visual and Auditory Receptive Fields View project

  title={Computational Modelling of Perceptual Music Features View project Normative Computational Theory of Visual and Auditory Receptive Fields View project},
  author={Anders Elowsson and Anders Friberg},
The spectral distribution of music audio has an important influence on listener perception, but large-scale characterizations are lacking. Therefore, the long-term average spectrum (LTAS) was analyzed for a large dataset of popular music. The mean LTAS was computed, visualized, and then approximated with two quadratic fittings. The fittings were subsequently used to derive the spectrum slope. By applying harmonic/percussive source separation, the relationship between LTAS and percussive… 

Figures and Tables from this paper


Predicting the perception of performed dynamics in music audio with ensemble learning.
Feature extraction methods were developed to capture relevant attributes related to spectral characteristics and spectral fluctuations, the latter through a sectional spectral flux, which highlighted the importance of source separation in the feature extraction.
Modelling the Speed of Music using Features from Harmonic/Percussive Separated Audio
A computational model of speed in music audio has been developed using a custom set of rhythmic features using listeners' ratings and the final models were able to explain about 90% of the variation in the training set, with little or no degradation for the test set.
Spectral distribution of solo voice and accompaniment in pop music
Long-term-average spectra of some orchestral accompaniments typically used in pop music are compared with those of classical symphonic orchestras and it is suggested that pop singers' difficulties to hear their own voices may be reduced if the frequency range 3-4 kHz is boosted in the monitor sound.
Spectral Characteristics of Popular Commercial Recordings 1950-2010
The aim was to analyze overall trends, as well as yearly and genre-specific ones, of a large dataset of popular commercial recordings and a novel method for averaging spectral distributions is proposed, which yields results that are prone to comparison.
Absolute amplitudes and spectra of certain musical instruments and orchestras
Measurements made on instruments and orchestras, during the playing of selections, include average amplitudes in long intervals (15 seconds) and distribution of peaks in very short intervals
Modeling the perception of tempo.
A system is proposed in which rhythmic representations are used to model the perception of tempo in music. The system can be understood as a five-layered model, where representations are transformed
Hi‐Fi voice: observations on the distribution of energy in the singing voice spectrum above 5 kHz
Current audio technology enables the weak spectrum of the voice above 4‐5 kHz to be studied reliably. It is known that energy in the 5‐20 kHz range can be perceived even when it is 50 dB or more
A perceptual assistant to do sound equalization
An intelligent interface to assist in the expert perceptual task of sound equalization using inductive learning to acquire expert skill using nearest neighbor pattern recognition and shows that the nearest-neighbor context-dependent equalization is higher than the set linear average equalization and that it is preferred 81% of the time.
Beat Tracking with a Cepstroid Invariant Neural Network
A novel rhythm tracking architecture that learns how to track tempo and beats through layered learning, and uses a neural network that is invariant with regards to the cepstroid length.
Harmonic/Percussive Separation Using Median Filtering
In this paper, we present a fast, simple and effective method to separate the harmonic and percussive parts of a monaural audio signal. The technique involves the use of median filtering on a