Search Results - "Simsekli, Umut"

Synchronizing Probability Measures on Rotations via Optimal Transport by Birdal, Tolga, Arbel, Michael, Simsekli, Umut, Guibas, Leonidas J.

“…We introduce a new paradigm, `measure synchronization', for synchronizing graphs with measure-valued edges. We formulate this problem as maximization of the…”
Get full text

A generative model for non-Intrusive load monitoring in commercial buildings by Henriet, Simon, Şimşekli, Umut, Fuentes, Benoit, Richard, Gaël

“…In the recent years, there has been an increasing academic and industrial interest for analyzing the electrical consumption of commercial buildings. Whilst…”
Get full text

Groove2Groove: One-Shot Music Style Transfer With Supervision From Synthetic Data by Cifka, Ondrej, Simsekli, Umut, Richard, Gael

“…Style transfer is the process of changing the style of an image, video, audio clip or musical piece so as to match the style of a given example. Even though…”
Get full text

Alpha-Stable Matrix Factorization by Simsekli, Umut, Liutkus, Antoine, Cemgil, Ali Taylan

“…Matrix factorization (MF) models have been widely used in data analysis. Even though they have been shown to be useful in many applications, classical MF…”
Get full text

Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytope by Birdal, Tolga, Simsekli, Umut

“…We present an entirely new geometric and probabilistic approach to synchronization of correspondences across multiple sets of objects or images. In particular,…”
Get full text

Speech Enhancement with Variational Autoencoders and Alpha-stable Distributions by Leglaive, Simon, Simsekli, Umut, Liutkus, Antoine, Girin, Laurent, Horaud, Radu

“…This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of…”
Get full text

Generalized Sliced Probability Metrics by Kolouri, Soheil, Nadjahi, Kimia, Shahrampour, Shahin, Simsekli, Umut

“…Sliced probability metrics have become increasingly popular in machine learning, and they play a quintessential role in various applications, including…”
Get full text

Bayesian Allocation Model: Marginal Likelihood-Based Model Selection for Count Tensors by Yldrm, Sinan, Kurutmaz, M. Burak, Barsbey, Melih, Simsekli, Umut, Cemgil, A. Taylan

“…In this article, we introduce a dynamic generative model, the Bayesian allocation model (BAM), for modeling count data. BAM covers various probabilistic…”
Get full text

Independent-Variation Matrix Factorization With Application to Energy Disaggregation by Henriet, Simon, Simsekli, Umut, Santos, Sergio Dos, Fuentes, Benoit, Richard, Gael

“…Matrix factorization techniques have proven to be useful in many unsupervised learning applications. Such techniques have been recently applied to Non…”
Get full text

Approximate Bayesian Computation with the Sliced-Wasserstein Distance by Nadjahi, Kimia, Bortoli, Valentin De, Durmus, Alain, Badeau, Roland, Simsekli, Umut

“…Approximate Bayesian Computation (ABC) is a popular method for approximate inference in generative models with intractable but easy-to-sample likelihood. It…”
Get full text

Self-Supervised VQ-VAE for One-Shot Music Style Transfer by Cifka, Ondrej, Ozerov, Alexey, Simsekli, Umut, Richard, Gael

“…Neural style transfer, allowing to apply the artistic style of one image to another, has become one of the most widely showcased computer vision applications…”
Get full text

Non-negative tensor factorization models for Bayesian audio processing by Şimşekli, Umut, Virtanen, Tuomas, Cemgil, Ali Taylan

“…We provide an overview of matrix and tensor factorization methods from a Bayesian perspective, giving emphasis on both the inference methods and modeling…”
Get full text

Efficient Bayesian Model Selection in PARAFAC via Stochastic Thermodynamic Integration by Nguyen, Thanh Huy, Simsekli, Umut, Richard, Gael, Cemgil, Ali Taylan

“…Parallel factor analysis (PARAFAC) is one of the most popular tensor factorization models. Even though it has proven successful in diverse application fields,…”
Get full text

Automatic Music Genre Classification Using Bass Lines by Şimşekli, Umut

“…A bass line is an instrumental melody that encapsulates both rhythmic, melodic, and harmonic features and arguably contains sufficient information for accurate…”
Get full text

A framework for parallel second order incremental optimization algorithms for solving partially separable problems by Kaya, Kamer, Öztoprak, Figen, Birbil, Ş. İlker, Cemgil, A. Taylan, Şimşekli, Umut, Kuru, Nurdan, Koptagel, Hazal, Öztürk, M. Kaan

“…We propose Hessian Approximated Multiple Subsets Iteration (HAMSI), which is a generic second order incremental algorithm for solving large-scale partially…”
Get full text

Alpha-Stable Low-Rank Plus Residual Decomposition for Speech Enhancement by Simsekli, Umut, Erdogan, Halil, Leglaive, Simon, Liutkus, Antoine, Badeau, Roland, Richard, Gael

“…In this study, we propose a novel probabilistic model for separating clean speech signals from noisy mixtures by decomposing the mixture spectra into a…”
Get full text

Non-negative source-filter dynamical system for speech enhancement by Simsekli, Umut, Le Roux, Jonathan, Hershey, John R.

“…Model-based speech enhancement methods, which rely on separately modeling the speech and the noise, have been shown to be powerful in many different problem…”
Get full text

Alpha-stable multichannel audio source separation by Leglaive, Simon, Simsekli, Umut, Liutkus, Antoine, Badeau, Roland, Richard, Gael

“…In this paper, we focus on modeling multichannel audio signals in the short-time Fourier transform domain for the purpose of source separation. We propose a…”
Get full text

Probabilistic Models for Real-time Acoustic Event Detection with Application to Pitch Tracking by Şimşekli, Umut, Cemgil, Ali Taylan

“…In this paper we present two probabilistic models for real-time acoustic event detection: the Hidden Markov Model and the Change Point Model. We construct the…”
Get full text

Randomized Matrix Decompositions and Exemplar Selection in Large Dictionaries for Polyphonic Piano Transcription by Arı, İsmail, Şimşekli, Umut, Cemgil, Ali Taylan, Akarun, Lale

“…Non-negative matrix factorization has been shown to be powerful for modelling audio signals. Many useful applications based on NMF, including musical source…”
Get full text