Matthew Davies

Abstract
In this paper, we address a subtopic of the broad domain of audio enhancement, namely musical audio bandwidth extension. We formulate the bandwidth extension problem using deep neural networks, where a band-limited signal is provided as input to the network, with the goal of reconstructing a full-bandwidth output. Our main contribution centers on the impact of the choice of low-pass filter when training and subsequently testing the network. For two different state-of-the-art deep architectures, ResNet and U-Net, we demonstrate that when the training and testing filters are matched, improvements in signal-to-noise ratio (SNR) of up to 7 dB can be obtained. However, when these filters differ, the improvement falls considerably and under some training conditions results in a lower SNR than the band-limited input. To circumvent this apparent overfitting to filter shape, we propose a data augmentation strategy which utilizes multiple low-pass filters during training and leads to improved generalization to unseen filtering conditions at test time.

Abstract
In this paper, we present TIV.lib, an open-source library for the content-based tonal description of musical audio signals. Its main novelty relies on the perceptually-inspired Tonal Interval Vector space based on the Discrete Fourier transform, from which multiple instantaneous and global representations, descriptors and metrics are computed-e.g., harmonic change, dissonance, diatonicity, and musical key. The library is cross-platform, implemented in Python and the graphical programming language Pure Data, and can be used in both online and offline scenarios. Of note is its potential for enhanced Music Information Retrieval, where tonal descriptors sit at the core of numerous methods and applications.

Abstract
We propose the use of Temporal Convolutional Networks for audio-based beat tracking. By contrasting our convolutional approach with the current state-of-the-art recurrent approach using Bidirectional Long Short-Term Memory, we demonstrate three highly promising attributes of TCNs for music analysis, namely: i) they achieve state-of-the-art performance on a wide range of existing beat tracking datasets, ii) they are well suited to parallelisation and thus can be trained efficiently even on very large training data; and iii) they require a small number of weights. © 2019 IEEE

Abstract
In this paper we present SEED, a generative system capable of arbitrarily extending recorded environmental sounds while preserving their inherent structure. The system architecture is grounded in concepts from concatenative sound synthesis and includes three top-level modules for segmentation, analysis, and generation. An input audio signal is first temporally segmented into a collection of audio segments, which are then reduced into a dictionary of audio classes by means of an agglomerative clustering algorithm. This representation, together with a concatenation cost between audio segment boundaries, is finally used to generate sequences of audio segments with arbitrarily long duration. The system output can be varied in the generation process by the simple and yet effective parametric control over the creation of the natural, temporally coherent, and varied audio renderings of environmental sounds. Copyright: © 2016 First author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License 3.0 Unported, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Abstract
We propose a multi-task learning approach for simultaneous tempo estimation and beat tracking of musical audio. The system shows state-of-the-art performance for both tasks on a wide range of data, but has another fundamental advantage: due to its multi-task nature, it is not only able to exploit the mutual information of both tasks by learning a common, shared representation, but can also improve one by learning only from the other. The multi-task learning is achieved by globally aggregating the skip connections of a beat tracking system built around temporal convolutional networks, and feeding them into a tempo classification layer. The benefit of this approach is investigated by the inclusion of training data for which tempo-only annotations are available, and which is shown to provide improvements in beat tracking accuracy.