Exact multiplicative updates for convolutional $\beta$-NMF in 2D

Autor: T., Pedro J. Villasana, Gorlow, Stanislaw

Publikováno v: 2019 27th European Signal Processing Conference (EUSIPCO)

In this paper, we extend the $\beta$-CNMF to two dimensions and derive exact multiplicative updates for its factors. The new updates generalize and correct the nonnegative matrix factor deconvolution previously proposed by Schmidt and M{\o}rup. We sh

Externí odkaz: http://arxiv.org/abs/1811.01661

Multiplicative Updates for Convolutional NMF Under $\beta$-Divergence

Autor: T., Pedro J. Villasana, Gorlow, Stanislaw, Hariraman, Arvind T.

Publikováno v: Optim Lett (2019)

In this letter, we generalize the convolutional NMF by taking the $\beta$-divergence as the contrast function and present the correct multiplicative updates for its factors in closed form. The new updates unify the $\beta$-NMF and the convolutional N

Externí odkaz: http://arxiv.org/abs/1803.05159

Decision-Based Transcription of Jazz Guitar Solos Using a Harmonic Bident Analysis Filter Bank and Spectral Distribution Weighting

Autor: Gorlow, Stanislaw, Ramona, Mathieu, Pachet, François

Jazz guitar solos are improvised melody lines played on one instrument on top of a chordal accompaniment (comping). As the improvisation happens spontaneously, a reference score is non-existent, only a lead sheet. There are situations, however, when

Externí odkaz: http://arxiv.org/abs/1611.06505

Coding Backward Compatible Audio Objects with Predictable Quality in a Very Spatial Way

Autor: Gorlow, Stanislaw

Publikováno v: 139th Audio Engineering Society (AES) Convention
139th Audio Engineering Society (AES) Convention, Oct 2015, New York, NY, United States. pp.4

International audience; A gradual transition from channel-based to object-based audio can currently be observed throughout the film and the broadcast industries. One paramount example of this trend is the new MPEG-H 3D Audio standard, which is under

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7d9dc69db15e75de848bbd180c7cee6d
https://hal.archives-ouvertes.fr/hal-01251648

On the Informed Source Separation Approach for Interactive Remixing in Stereo

Autor: Gorlow, Stanislaw, Marchand, Sylvain

Publikováno v: 134th Audio Engineering Society (AES) Convention
134th Audio Engineering Society (AES) Convention, May 2013, Rome, Italy

International audience; Informed source separation (ISS) has become a popular trend in the audio signal processing community over the past few years. Its purpose is to decompose a mixture signal into its constituent parts at the desired or the best p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e06d02d1faa964d813951b900d9d7314
https://hal.archives-ouvertes.fr/hal-00788429