Hierarchical taxonomies are common in many contexts, and they are a very natural structure humans use to organise information. In machine learning, the family of methods that use the 'extra' information is called hierarchical classification. However, applied to audio classification, this remains relatively unexplored. Here we focus on how to integrate the hierarchical information of a problem to learn embeddings representative of the hierarchical relationships. Previously, triplet loss has been proposed to address this problem, however it presents some issues like requiring the careful construction of the triplets, and being limited in the extent of hierarchical information it uses at each iteration. In this work we propose a rank based loss function that uses hierarchical information and translates this into a rank ordering of target distances between the examples. We show that rank based loss is suitable to learn hierarchical representations of the data. By testing on unseen fine level classes we show that this method is also capable of learning hierarchically correct representations of the new classes. Rank based loss has two promising aspects, it is generalisable to hierarchies with any number of levels, and is capable of dealing with data with incomplete hierarchical labels.

A typical audio signal processing pipeline includes multiple disjoint analysis stages, including calculation of a time-frequency representation followed by spectrogram-based feature analysis. We show how time-frequency analysis and nonnegative matrix factorisation can be jointly formulated as a spectral mixture Gaussian process model with nonstationary priors over the amplitude variance parameters. Further, we formulate this nonlinear model's state space representation, making it amenable to infinite-horizon Gaussian process regression with approximate inference via expectation propagation, which scales linearly in the number of time steps and quadratically in the state dimensionality. By doing so, we are able to process audio signals with hundreds of thousands of data points. We demonstrate, on various tasks with empirical data, how this inference scheme outperforms more standard techniques that rely on extended Kalman filtering.

In audio signal processing, probabilistic time-frequency models have many benefits over their non-probabilistic counterparts. They adapt to the incoming signal, quantify uncertainty, and measure correlation between the signal's amplitude and phase information, making time domain resynthesis straightforward. However, these models are still not widely used since they come at a high computational cost, and because they are formulated in such a way that it can be difficult to interpret all the modelling assumptions. By showing their equivalence to Spectral Mixture Gaussian processes, we illuminate the underlying model assumptions and provide a general framework for constructing more complex models that better approximate real-world signals. Our interpretation makes it intuitive to inspect, compare, and alter the models since all prior knowledge is encoded in the Gaussian process kernel functions. We utilise a state space representation to perform efficient inference via Kalman smoothing, and we demonstrate how our interpretation allows for efficient parameter learning in the frequency domain.

Gaussian process (GP) audio source separation is a time-domain approach that circumvents the inherent phase approximation issue of spectrogram based methods. Furthermore, through its kernel, GPs elegantly incorporate prior knowledge about the sources into the separation model. Despite these compelling advantages, the computational complexity of GP inference scales cubically with the number of audio samples. As a result, source separation GP models have been restricted to the analysis of short audio frames. We introduce an efficient application of GPs to time-domain audio source separation, without compromising performance. For this purpose, we used GP regression, together with spectral mixture kernels, and variational sparse GPs. We compared our method with LD-PSDTF (positive semi-definite tensor factorization), KL-NMF (Kullback-Leibler non-negative matrix factorization), and IS-NMF (Itakura-Saito NMF). Results show that the proposed method outperforms these techniques.

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most datasets are "weakly labelled" having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose a data-efficient training of a stacked convolutional and recurrent neural network. This neural network is trained in a multi instance learning setting for which we introduce a new loss function that leads to improved training compared to the usual approaches for weakly supervised learning. We successfully test our approach on two low-resource datasets that lack temporal labels.

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.

Recent advances in analysis of subband amplitude envelopes of natural sounds have resulted in convincing synthesis, showing subband amplitudes to be a crucial component of perception. Probabilistic latent variable analysis is particularly revealing, but existing approaches don't incorporate prior knowledge about the physical behaviour of amplitude envelopes, such as exponential decay and feedback. We use latent force modelling, a probabilistic learning paradigm that incorporates physical knowledge into Gaussian process regression, to model correlation across spectral subband envelopes. We augment the standard latent force model approach by explicitly modelling correlations over multiple time steps. Incorporating this prior knowledge strengthens the interpretation of the latent functions as the source that generated the signal. We examine this interpretation via an experiment which shows that sounds generated by sampling from our probabilistic model are perceived to be more realistic than those generated by similar models based on nonnegative matrix factorisation, even in cases where our model is outperformed from a reconstruction error perspective.

Automatic music transcription (AMT) aims to infer a latent symbolic representation of a piece of music (piano-roll), given a corresponding observed audio recording. Transcribing polyphonic music (when multiple notes are played simultaneously) is a challenging problem, due to highly structured overlapping between harmonics. We study whether the introduction of physically inspired Gaussian process (GP) priors into audio content analysis models improves the extraction of patterns required for AMT. Audio signals are described as a linear combination of sources. Each source is decomposed into the product of an amplitude-envelope, and a quasi-periodic component process. We introduce the Mat\'ern spectral mixture (MSM) kernel for describing frequency content of singles notes. We consider two different regression approaches. In the sigmoid model every pitch-activation is independently non-linear transformed. In the softmax model several activation GPs are jointly non-linearly transformed. This introduce cross-correlation between activations. We use variational Bayes for approximate inference. We empirically evaluate how these models work in practice transcribing polyphonic music. We demonstrate that rather than encourage dependency between activations, what is relevant for improving pitch detection is to learnt priors that fit the frequency content of the sound events to detect.

Real music signals are highly variable, yet they have strong statistical structure. Prior information about the underlying physical mechanisms by which sounds are generated and rules by which complex sound structure is constructed (notes, chords, a complete musical score), can be naturally unified using Bayesian modelling techniques. Typically algorithms for Automatic Music Transcription independently carry out individual tasks such as multiple-F0 detection and beat tracking. The challenge remains to perform joint estimation of all parameters. We present a Bayesian approach for modelling music audio, and content analysis. The proposed methodology based on Gaussian processes seeks joint estimation of multiple music concepts by incorporating into the kernel prior information about non-stationary behaviour, dynamics, and rich spectral content present in the modelled music signal. We illustrate the benefits of this approach via two tasks: pitch estimation, and inferring missing segments in a polyphonic audio recording.

We describe an inference task in which a set of timestamped event observations must be clustered into an unknown number of temporal sequences with independent and varying rates of observations. Various existing approaches to multi-object tracking assume a fixed number of sources and/or a fixed observation rate; we develop an approach to inferring structure in timestamped data produced by a mixture of an unknown and varying number of similar Markov renewal processes, plus independent clutter noise. The inference simultaneously distinguishes signal from noise as well as clustering signal observations into separate source streams. We illustrate the technique via a synthetic experiment as well as an experiment to track a mixture of singing birds.