Related papers: On loss functions and evaluation metrics for music…

This dissertation proposes the study of multimodal learning in the context of musical signals. Throughout, we focus on the interaction between audio signals and text information. Among the many text sources related to music that can be used…

Loss functions are error metrics that quantify the difference between a prediction and its corresponding ground truth. Fundamentally, they define a functional landscape for traversal by gradient descent. Although numerous loss functions…

The Relative Transfer Matrix (ReTM), recently introduced as a generalization of the relative transfer function for multiple receivers and sources, shows promising performance when applied to speech enhancement and speaker separation in…

We revisit the source image estimation problem from blind source separation (BSS). We generalize the traditional minimum distortion principle to maximum likelihood estimation with a model for the residual spectrograms. Because residual…

Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the underlying properties of these embeddings remain underexplored.…

Measuring inconsistency is viewed as an important issue related to handling inconsistencies. Good measures are supposed to satisfy a set of rational properties. However, defining sound properties is sometimes problematic. In this paper, we…

Reliability of machine learning evaluation -- the consistency of observed evaluation scores across replicated model training runs -- is affected by several sources of nondeterminism which can be regarded as measurement noise. Current…

The Inaugural Music Source Restoration (MSR) Challenge targets the recovery of original, unprocessed stems from fully mixed and mastered music. Unlike conventional music source separation, MSR requires reversing complex production processes…

Music source separation performance has greatly improved in recent years with the advent of approaches based on deep learning. Such methods typically require large amounts of labelled training data, which in the case of music consist of…

In Gaussian model-based multichannel audio source separation, the likelihood of observed mixtures of source signals is parametrized by source spectral variances and by associated spatial covariance matrices. These parameters are estimated…

We propose a knowledge-driven, model-based approach to segmenting audio into single-category and mixed-category chunks with applications to source separation. "Knowledge" here denotes information associated with the data, such as music…

Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model? We present an extension of the Wave-U-Net model which allows end-to-end monaural source separation with a non-fixed number…

We propose an algorithm for the blind separation of single-channel audio signals. It is based on a parametric model that describes the spectral properties of the sounds of musical instruments independently of pitch. We develop a novel…

Music Information Retrieval (MIR) research is increasingly leveraging representation learning to obtain more compact, powerful music audio representations for various downstream MIR tasks. However, current representation evaluation methods…

Computing the rate-distortion function for continuous sources is commonly regarded as a standard continuous optimization problem. When numerically addressing this problem, a typical approach involves discretizing the source space and…

In epidemiological studies, participants' disease status is often collected through self-reported outcomes in place of formal medical tests due to budget constraints. However, self-reported outcomes are often subject to measurement errors,…

To evaluate disentangled representations several metrics have been proposed. However, theoretical guarantees for conventional metrics of disentanglement are missing. Moreover, conventional metrics do not have a consistent correlation with…

Mitigating the negative impact of noisy labels has been aperennial issue in supervised learning. Robust loss functions have emerged as a prevalent solution to this problem. In this work, we introduce the Variation Ratio as a novel property…

Supervised deep learning methods for performing audio source separation can be very effective in domains where there is a large amount of training data. While some music domains have enough data suitable for training a separation system,…

Noise power estimation is a key issue in modern wireless communication systems. It allows resource allocation by detecting white spectral spaces effectively, and gives control over the communication process by adjusting transmission power.…