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

Abstract

This paper describes a sound source separation method for polyphonic sound mixtures of music to build an instrument equalizer for remixing multiple tracks separated from compact-disc recordings by changing the volume level of each track. Although such mixtures usually include both harmonic and inharmonic sounds, the dif culties in dealing with both types of sounds together have not been addressed in most previous methods that have focused on either of the two types separately. We therefore developed an integrated weighted-mixture model consisting of both harmonic-structure and inharmonic-structure tone models (generative models for the power spectrogram). On the basis of the MAP estimation using the EM algorithm, we estimated all model parameters of this integrated model under several original constraints for preventing over-training and maintaining intra-instrument consistency. Using standard MIDI les as prior information of the model parameters, we applied this model to compact-disc recordings and achieved the instrument equalizer.

Polyphonic audio-to-score alignment based on Bayesian Latent Harmonic Allocation Hidden Markov Model

“…It is required whenever a system needs to coordinate a music score (e.g. a standard MIDI file) and an audio signal, such as score-informed source separation [1,2], or score-informed analysis of music performance [3,4,5,6,7].…”

Parameter Estimation for Harmonic and Inharmonic Models by Using Timbre Feature Distributions

“…We therefore propose a sound source separation method 11) that represents the input polyphonic audio signal as a mixture of both harmonic and inharmonic tone models that correspond to musical notes. We assume that a standard MIDI file (SMF) synchronized with the input audio signal is available as prior information 1 .…”

Polyphonic Pitch Estimation and Instrument Identification by Joint Modeling of Sustained and Attack Sounds

“…Our model differs from the nonparametric inharmonic model in [25] in two ways: it does not represent sustained inharmonic sounds but the attack part only and it involves much fewer parameters due to its parametric expression. These two differences make sense in our application context, where no prior information is available contrary to the informed source separation context in [25] where pitch, onset, duration and instrument are known.…”

“…Designing an instrument model able to deal both with harmonic and inharmonic features is essential for reflecting the timbre Polyphonic pitch estimation and instrument identification by joint modeling of sustained and attack sounds characteristics of any musical instrument. In [25], a joint parametric harmonic and non-parametric inharmonic model was proposed and used for source separation given the pitch and instrument of all notes. In [26], we defined a joint parametric model of harmonic and attack sounds but considered timbre features derived from the harmonic part only.…”