Search Results - "Widmer, Gerhard"

Real-Time Music Following in Score Sheet Images via Multi-Resolution Prediction by Henkel , Florian, Widmer , Gerhard

“…The task of real-time alignment between a music performance and the corresponding score (sheet music), also known as score following, poses a challenging…”
Get full text

Imposing Higher-Level Structure in Polyphonic Music Generation Using Convolutional Restricted Boltzmann Machines and Constraints by Widmer, Gerhard, Grachten, Maarten, Lattner, Stefan

“…We introduce a method for imposing higher-level structure on generated, polyphonic music. A Convolutional Restricted Boltzmann Machine (C-RBM) as a generative…”
Get full text

An evaluation of linear and non-linear models of expressive dynamics in classical piano and symphonic music by Cancino-Chacón, Carlos Eduardo, Gadermaier, Thassilo, Widmer, Gerhard, Grachten, Maarten

“…Expressive interpretation forms an important but complex aspect of music, particularly in Western classical music. Modeling the relation between musical…”
Get full text

Score Following as a Multi-Modal Reinforcement Learning Problem by Henkel, Florian, Balke, Stefan, Dorfer, Matthias, Widmer, Gerhard

“…Score following is the process of tracking a musical performance (audio) in a corresponding symbolic representation (score). While methods using…”
Get full text

Balancing bias and performance in polyphonic piano transcription systems by Marták, Lukáš Samuel, Kelz , Rainer, Widmer , Gerhard

“…Current state-of-the-art methods for polyphonic piano transcription tend to use high capacity neural networks. Most models are trained “end-to-end”, and learn…”
Get full text

On End-to-End White-Box Adversarial Attacks in Music Information Retrieval by Prinz, Katharina, Flexer, Arthur, Widmer, Gerhard

“…Small adversarial perturbations of input data can drastically change the performance of machine learning systems, thereby challenging their validity. We…”
Get full text

Differentiable Short-Term Models for Efficient Online Learning and Prediction in Monophonic Music by Bjare, Mathias Rose, Lattner, Stefan, Widmer, Gerhard

“…As pieces of music are usually highly self-similar, online-learning short-term models are well-suited for musical sequence prediction tasks. Due to their…”
Get full text

DExter: Learning and Controlling Performance Expression with Diffusion Models by Zhang, Huan, Chowdhury, Shreyan, Cancino-Chacón, Carlos Eduardo, Liang, Jinhua, Dixon, Simon, Widmer, Gerhard

“…In the pursuit of developing expressive music performance models using artificial intelligence, this paper introduces DExter, a new approach leveraging…”
Get full text

Automatic Note-Level Score-to-Performance Alignments in the ASAP Dataset by Peter, Silvan David, Cancino-Chacón, Carlos Eduardo, Foscarin, Francesco, McLeod, Andrew Philip, Henkel, Florian, Karystinaios, Emmanouil, Widmer, Gerhard

“…Several MIR applications require fine-grained note alignments between MIDI performances and their musical scores for training and evaluation. However, large…”
Get full text

Linear Basis Models for Prediction and Analysis of Musical Expression by Grachten, Maarten, Widmer, Gerhard

“…The quest for understanding how pianists interpret notated music to turn it into a lively musical experience, has led to numerous models of musical expression…”
Get full text

Inferring Metrical Structure in Music Using Particle Filters by Krebs, Florian, Holzapfel, Andre, Cemgil, Ali Taylan, Widmer, Gerhard

“…In this paper, we propose a new state-of-the-art particle filter (PF) system to infer the metrical structure of musical audio signals. The new inference method…”
Get full text

A fast audio similarity retrieval method for millions of music tracks by Schnitzer, Dominik, Flexer, Arthur, Widmer, Gerhard

“…We present a filter-and-refine method to speed up nearest neighbor searches with the Kullback–Leibler divergence for multivariate Gaussians. This combination…”
Get full text

A fully convolutional deep auditory model for musical chord recognition by Korzeniowski, Filip, Widmer, Gerhard

“…Chord recognition systems depend on robust feature extraction pipelines. While these pipelines are traditionally hand-crafted, recent advances in end-to-end…”
Get full text

Learning Audio–Sheet Music Correspondences for Cross-Modal Retrieval and Piece Identification by Dorfer, Matthias, Hajič jr, Jan, Arzt, Andreas, Frostel, Harald, Widmer, Gerhard

“…This work addresses the problem of matching musical audio directly to sheet music, without any higher-level abstract representation. We propose a method that…”
Get full text

Investigations of Between-Hand Synchronization in Magaloffs Chopin by Goebl, Werner, Flossmann, Sebastian, Widmer, Gerhard

“…This article presents research towards automated computational analysis of large corpora of music performance data. In particular, we focus on between-hand…”
Get full text

Phase-plane Representation and Visualization of Gestural Structure in Expressive Timing by Grachten, Maarten, Goebl, Werner, Flossmann, Sebastian, Widmer, Gerhard

“…For the past few decades there has been considerable scientific interest in expression in music performance (Gabrielsson, 2003 ). A particularly relevant…”
Get full text

Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks by Koutini, Khaled, Eghbal-zadeh, Hamid, Widmer, Gerhard

“…In this paper, we study the performance of variants of well-known Convolutional Neural Network (CNN) architectures on different audio tasks. We show that…”
Get full text

Efficient Large-Scale Audio Tagging Via Transformer-to-CNN Knowledge Distillation by Schmid, Florian, Koutini, Khaled, Widmer, Gerhard

“…Audio Spectrogram Transformer models rule the field of Audio Tagging, outrunning previously dominating Convolutional Neural Networks (CNNs). Their superiority…”
Get full text

Towards Explaining Expressive Qualities in Piano Recordings: Transfer of Explanatory Features Via Acoustic Domain Adaptation by Chowdhury, Shreyan, Widmer, Gerhard

“…Emotion and expressivity in music have been topics of considerable interest in the field of music information retrieval. In recent years, mid-level perceptual…”
Get full text

Robust Quad-Based Audio Fingerprinting by Sonnleitner, Reinhard, Widmer, Gerhard

“…We propose an audio fingerprinting method that adapts findings from the field of blind astrometry to define simple, efficiently representable characteristic…”
Get full text