Consistent Spectrogram Separation from Nonstationary Mixture - FAYOL - Institut Henri Fayol
Conference Papers Year : 2024

Consistent Spectrogram Separation from Nonstationary Mixture

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.
Fichier principal
Vignette du fichier
KM2024.pdf (8.44 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04621727 , version 1 (24-06-2024)

Identifiers

  • HAL Id : hal-04621727 , version 1

Cite

Ama Marina Kreme, Adrien Meynard. Consistent Spectrogram Separation from Nonstationary Mixture. EUSIPCO 2024, Aug 2024, Lyon, France. ⟨hal-04621727⟩
184 View
25 Download

Share

More