Common fate models for unison source separation

Fabian-Robert Stöter, Antoine Liutkus, Roland Badeau, Paul Magron, Bernd Edler

Tutkimustuotos: KonferenssiartikkeliTieteellinenvertaisarvioitu

25 Sitaatiot (Scopus)

Abstrakti

In this paper we present a novel source separation method aiming to overcome the difficulty of modelling non-stationary signals. The method can be applied to mixtures of musical instruments with frequency and/or amplitude modulation, e.g. typically caused by vi-brato. It is based on a signal representation that divides the complex spectrogram into a grid of patches of arbitrary size. These complex patches are then processed by a two-dimensional discrete Fourier transform, forming a tensor representation which reveals spectral and temporal modulation textures. Our representation can be seen as an alternative to modulation transforms computed on magnitude spectrograms. An adapted factorization model allows to decompose different time-varying harmonic sources based on their particular common modulation profile: hence the name Common Fate Model. The method is evaluated on musical instrument mixtures playing the same fundamental frequency (unison), showing improvement over other state-of-the-art methods.
AlkuperäiskieliEnglanti
OtsikkoInternational Conference on Acoustics, Speech and Signal Processing
DOI - pysyväislinkit
TilaJulkaistu - maalisk. 2016
Julkaistu ulkoisestiKyllä
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
Tapahtuma41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, Kiina
Kesto: 20 maalisk. 201625 maalisk. 2016

Conference

Conference41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Maa/AlueKiina
KaupunkiShanghai
Ajanjakso20/03/1625/03/16

Sormenjälki

Sukella tutkimusaiheisiin 'Common fate models for unison source separation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä