2 code implementations • 25 Jul 2023 • Vincent Lostanlen, Daniel Haider, Han Han, Mathieu Lagrange, Peter Balazs, Martin Ehler
Waveform-based deep learning faces a dilemma between nonparametric and parametric approaches.
1 code implementation • 24 Jan 2023 • Cyrus Vahidi, Han Han, Changhong Wang, Mathieu Lagrange, György Fazekas, Vincent Lostanlen
Computer musicians refer to mesostructures as the intermediate levels of articulation between the microstructure of waveshapes and the macrostructure of musical forms.
1 code implementation • 7 Jan 2023 • Han Han, Vincent Lostanlen, Mathieu Lagrange
On the other hand, mean square error in the spectrotemporal domain, known as "spectral loss", is perceptually motivated and serves in differentiable digital signal processing (DDSP).
3 code implementations • 18 Apr 2022 • John Muradeli, Cyrus Vahidi, Changhong Wang, Han Han, Vincent Lostanlen, Mathieu Lagrange, George Fazekas
Joint time-frequency scattering (JTFS) is a convolutional operator in the time-frequency domain which extracts spectrotemporal modulations at various rates and scales.
1 code implementation • 21 Jul 2020 • Vincent Lostanlen, Christian El-Hajj, Mathias Rossignol, Grégoire Lafay, Joakim andén, Mathieu Lagrange
Furthermore, it minimizes triplet loss in the cluster graph by means of the large-margin nearest neighbor (LMNN) metric learning algorithm.
no code implementations • 15 Nov 2017 • Grégoire Lafay, Emmanouil Benetos, Mathieu Lagrange
As part of the 2016 public evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2016), the second task focused on evaluating sound event detection systems using synthetic mixtures of office sounds.
no code implementations • 31 Jan 2015 • Mathieu Lagrange, Grégoire Lafay, Mathias Rossignol, Emmanouil Benetos, Axel Roebel
This paper introduces a model of environmental acoustic scenes which adopts a morphological approach by ab-stracting temporal structures of acoustic scenes.
no code implementations • 11 Dec 2014 • Mathieu Lagrange, Grégoire Lafay, Boris Defreville, Jean-Julien Aucouturier
The "bag-of-frames" approach (BOF), which encodes audio signals as the long-term statistical distribution of short-term spectral features, is commonly regarded as an effective and sufficient way to represent environmental sound recordings (soundscapes) since its introduction in an influential 2007 article.