Passer à la navigation principale Passer à la recherche Passer au contenu principal

Nonnegative tensor factorization with frequency modulation cues for blind audio source separation

  • Analog Devices Lyric Labs
  • McGill University
  • Université Paris-Saclay

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

We present Vibrato Nonnegative Tensor Factorization, an algorithm for single-channel unsupervised audio source separation with an application to separating instrumental or vocal sources with nonstationary pitch from music recordings. Our approach extends Nonnegative Matrix Factorization for audio modeling by including local estimates of frequency modulation as cues in the separation. This permits the modeling and unsupervised separation of vibrato or glissando musical sources, which is not possible with the basic matrix factorization formulation. The algorithm factorizes a sparse nonnegative tensor comprising the audio spectrogram and local frequency-slope-to-frequency ratios, which are estimated at each time-frequency bin using the Distributed Derivative Method. The use of local frequency modulations as separation cues is motivated by the principle of common fate partial grouping from Auditory Scene Analysis, which hypothesizes that each latent source in a mixture is characterized perceptually by coherent frequency and amplitude modulations shared by its component partials. We derive multiplicative factor updates by Minorization-Maximization, which guarantees convergence to a local optimum by iteration. We then compare our method to the baseline on two separation tasks: one considers synthetic vibrato notes, while the other considers vibrato string instrument recordings.

langue originaleAnglais
titreProceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016
rédacteurs en chefMichael I. Mandel, Johanna Devaney, Douglas Turnbull, George Tzanetakis
EditeurInternational Society for Music Information Retrieval
Pages211-217
Nombre de pages7
ISBN (Electronique)9780692755068
étatPublié - 1 janv. 2016
Modification externeOui
Evénement17th International Society for Music Information Retrieval Conference, ISMIR 2016 - New York, États-Unis
Durée: 7 août 201611 août 2016

Série de publications

NomProceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016

Une conférence

Une conférence17th International Society for Music Information Retrieval Conference, ISMIR 2016
Pays/TerritoireÉtats-Unis
La villeNew York
période7/08/1611/08/16

Empreinte digitale

Examiner les sujets de recherche de « Nonnegative tensor factorization with frequency modulation cues for blind audio source separation ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation