Phase reconstruction of spectrograms based on a model of repeated audio events

TL;DR

This paper presents a new phase reconstruction method for spectrograms that leverages phase repetitions across onset frames to improve audio source separation, demonstrating promising results in complex mixtures.

Contribution

It introduces a novel phase estimation technique based on phase repetitions and a reference phase model, advancing phase recovery in audio processing.

Findings

Model effectively exploits phase repetitions across onset frames.

Improves separation of overlapping audio components.

Demonstrates promising results in complex mixtures.

Abstract

Phase recovery of modified spectrograms is a major issue in audio signal processing applications, such as source separation. This paper introduces a novel technique for estimating the phases of components in complex mixtures within onset frames in the Time-Frequency (TF) domain. We propose to exploit the phase repetitions from one onset frame to another. We introduce a reference phase which characterizes a component independently of its activation times. The onset phases of a component are then modeled as the sum of this reference and an offset which is linearly dependent on the frequency. We derive a complex mixture model within onset frames and we provide two algorithms for the estimation of the model phase parameters. The model is estimated on experimental data and this technique is integrated into an audio source separation framework. The results demonstrate that this model is a promising tool for exploiting phase repetitions, and point out its potential for separating overlapping components in complex mixtures.