Search Results for author:
Found 9 papers, 5 papers with code
Signal Inpainting from Fourier Magnitudes
Signal inpainting is the task of restoring degraded or missing samples in a signal.
Algorithms for audio inpainting based on probabilistic nonnegative matrix factorization
First, we treat the missing samples as latent variables, and derive two expectation-maximization algorithms for estimating the parameters of the model, depending on whether we formulate the problem in the time- or time-frequency domain.
A majorization-minimization algorithm for nonnegative binary matrix factorization
We factorize the Bernoulli parameter and consider an additional Beta prior on one of the factors to further improve the model's expressive power.
A Sparsity-promoting Dictionary Model for Variational Autoencoders
Structuring the latent space in probabilistic deep generative models, e. g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting.
Neural content-aware collaborative filtering for cold-start music recommendation
In this work, we introduce neural content-aware collaborative filtering, a unified framework which alleviates these limits, and extends the recently introduced neural collaborative filtering to its content-aware counterpart.
Leveraging the structure of musical preference in content-aware music recommendation
These approaches are agnostic to the song content, and therefore face the cold-start problem: they cannot recommend novel songs without listening history.
Phase retrieval with Bregman divergences and application to audio signal recovery
Therefore, we formulate PR as a new minimization problem involving Bregman divergences.
Sound
Language Modelling for Sound Event Detection with Teacher Forcing and Scheduled Sampling
On the contrary, with our method there is a decrease of 4% at F1 score and an increase of 7% at ER for the TUT-SED Synthetic 2016 dataset.
Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification
A challenging problem in deep learning-based machine listening field is the degradation of the performance when using data from unseen conditions.
