Related papers: A Deep Representation for Invariance And Music Cla…
Deep neural networks have frequently been used to directly learn representations useful for a given task from raw input data. In terms of overall performance metrics, machine learning solutions employing deep representations frequently have…
Recently, deep representation learning has shown strong performance in multiple audio tasks. However, its use for learning spatial representations from multichannel audio is underexplored. We investigate the use of a pretraining stage based…
Music Inpainting is the task of filling in missing or lost information in a piece of music. We investigate this task from an interactive music creation perspective. To this end, a novel deep learning-based approach for musical score…
Reservoir computing is an emerging, but very successful approach towards processing and classification of various signals. It can be described as a model of a transient computation, where influence of input changes internal dynamics of…
Recent advances in image clustering typically focus on learning better deep representations. In contrast, we present an orthogonal approach that does not rely on abstract features but instead learns to predict image transformations and…
Deep representation learning is a crucial procedure in multimedia analysis and attracts increasing attention. Most of the popular techniques rely on convolutional neural network and require a large amount of labeled data in the training…
Self-supervised audio-visual source separation leverages natural correlations between audio and vision modalities to separate mixed audio signals. In this work, we first systematically analyse the performance of existing multimodal fusion…
A prominent theory of affective response to music revolves around the concepts of surprisal and expectation. In prior work, this idea has been operationalized in the form of probabilistic models of music which allow for precise computation…
We address the problem of improving the performance and in particular the sample complexity of deep neural networks by enforcing and guaranteeing invariances to symmetry transformations rather than learning them from data. Group-equivariant…
Accurate delineation of fine-scale structures is a very important yet challenging problem. Existing methods use topological information as an additional training loss, but are ultimately making pixel-wise predictions. In this paper, we…
In this work, we present a method for learning interpretable music signal representations directly from waveform signals. Our method can be trained using unsupervised objectives and relies on the denoising auto-encoder model that uses a…
In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose…
We propose in this work a multi-view learning approach for audio and music classification. Considering four typical low-level representations (i.e. different views) commonly used for audio and music recognition tasks, the proposed…
Classification of audio samples is an important part of many auditory systems. Deep learning models based on the Convolutional and the Recurrent layers are state-of-the-art in many such tasks. In this paper, we approach audio classification…
Multimodal affective computing aims to predict humans' sentiment, emotion, intention, and opinion using language, acoustic, and visual modalities. However, current models often learn spurious correlations that harm generalization under…
Sound can convey significant information for spatial reasoning in our daily lives. To endow deep networks with such ability, we address the challenge of dense indoor prediction with sound in both 2D and 3D via cross-modal knowledge…
A number of machine learning tasks entail a high degree of invariance: the data distribution does not change if we act on the data with a certain group of transformations. For instance, labels of images are invariant under translations of…
Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a…
Implicit neural representations (INRs) are a rapidly growing research field, which provides alternative ways to represent multimedia signals. Recent applications of INRs include image super-resolution, compression of high-dimensional…
Recent years have witnessed an increased interest in the application of persistent homology, a topological tool for data analysis, to machine learning problems. Persistent homology is known for its ability to numerically characterize the…