# Investigating the Potential of Pseudo Quadrature Mirror Filter-Banks in Music Source Separation Tasks

## TL;DR

This paper explores the use of optimized pseudo quadrature mirror filter-banks (PQMF) as a time-frequency representation for music source separation, demonstrating its effectiveness as an alternative to traditional methods.

## Contribution

It introduces the application of optimized PQMF in music source separation, highlighting its potential to preserve sparsity and disjointness properties of T-F representations.

## Key findings

- PQMF maintains sparsity and disjointness properties.
- PQMF can effectively represent musical signal mixtures.
- Experimental results support PQMF as a viable alternative.

## Abstract

Estimating audio and musical signals from single channel mixtures often, if not always, involves a transformation of the mixture signal to the time-frequency (T-F) domain in which a masking operation takes place. Masking is realized as an element-wise multiplication of the mixture signal's T-F representation with a ratio of computed sources' spectrogram. Studies have shown that the performance of the overall source estimation scheme is subject to the sparsity and disjointness properties of a given T-F representation. In this work we investigate the potential of an optimized pseudo quadrature mirror filter-bank (PQMF), as a T-F representation for music source separation tasks. Experimental results, suggest that the PQMF maintains the aforementioned desirable properties and can be regarded as an alternative for representing mixtures of musical signals.