Related papers: Learning Music Audio Representations With Limited …

Training of a Machine Learning model requires sufficient data. The sufficiency of the data is not always about the quantity, but about the relevancy and reduced redundancy. Data-generating processes create massive amounts of data. When used…

Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. To encourage learning…

Deep audio representation learning using multi-modal audio-visual data often leads to a better performance compared to uni-modal approaches. However, in real-world scenarios both modalities are not always available at the time of inference,…

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There…

Human perception and experience of music is highly context-dependent. Contextual variability contributes to differences in how we interpret and interact with music, challenging the design of robust models for information retrieval.…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…

The performance of deep learning models for music source separation heavily depends on training data quality. However, datasets are often corrupted by difficult-to-detect artifacts such as audio bleeding and label noise. Since the type and…

Music is a structured and perceptually rich sequence of sounds in time, whose perception is shaped by the interplay of expectation and uncertainty about what comes next. Yet the uncertainty we infer from music depends on how the musical…

The utilization of deep learning techniques in generating various contents (such as image, text, etc.) has become a trend. Especially music, the topic of this paper, has attracted widespread attention of countless researchers.The whole…

This paper studies practical limitations of learning methods for resource management in non-stationary radio environment. We propose two learning models carefully designed to support rate maximization objective under user mobility. We study…

We present a multimodal framework to learn general audio representations from videos. Existing contrastive audio representation learning methods mainly focus on using the audio modality alone during training. In this work, we show that…

Generating music is an interesting and challenging problem in the field of machine learning. Mimicking human creativity has been popular in recent years, especially in the field of computer vision and image processing. With the advent of…

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,…

Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and…

We propose a self-supervised algorithm to learn representations from egocentric video data. Recently, significant efforts have been made to capture humans interacting with their own environments as they go about their daily activities. In…

Most machine learning theory and practice is concerned with learning a single task. In this thesis it is argued that in general there is insufficient information in a single task for a learner to generalise well and that what is required…

Music representation learning is notoriously difficult for its complex human-related concepts contained in the sequence of numerical signals. To excavate better MUsic SEquence Representation from labeled audio, we propose a novel…

Advances in data acquisition and computational methods have accelerated the use of differential equation based modelling for complex systems. Such systems are often described by coupled (or more) variables, yet governing equation is…

In this paper, we consider the problem of probabilistically modelling symbolic music data. We introduce a representation which reduces polyphonic music to a univariate categorical sequence. In this way, we are able to apply state of the art…