Consistent Spectrogram Separation from Nonstationary Mixture
Signal Processing
2024-06-26 v1
Abstract
We present a spectrogram separation method tailored for mixtures comprising two nonstationary components. By exploiting the unique characteristics of their time-frequency representations, we propose an inverse problem formulation to estimate the spectrograms of the components. We then introduce an alternating optimization algorithm that ensures the consistency of the estimated spectrograms. The efficacy of the algorithm is evaluated through testing on synthetic mixtures and is applied to a bioacoustic signal.
Cite
@article{arxiv.2406.17314,
title = {Consistent Spectrogram Separation from Nonstationary Mixture},
author = {Adrien Meynard and Ama Marina Kreme},
journal= {arXiv preprint arXiv:2406.17314},
year = {2024}
}