Related papers: Unsupervised Evaluation of Deep Audio Embeddings f…

The ability of deep neural networks to learn complex data relations and representations is established nowadays, but it generally relies on large sets of training data. This work explores a "piece-specific" autoencoding scheme, in which a…

Failures or breakdowns in factory machinery can be costly to companies, so there is an increasing demand for automatic machine inspection. Existing approaches to acoustic signal-based unsupervised anomaly detection, such as those using a…

Human in-the-loop quality assurance (QA) is typically performed after medical image segmentation to ensure that the systems are performing as intended, as well as identifying and excluding outliers. By performing QA on large-scale,…

A general non-Gaussian semiparametric model is adopted to characterize the measurement vectors, i.e.\ the \textit{snapshots}, collected by a linear array. Moreover, the recently derived \textit{robust semiparametric efficient} $R$-estimator…

In the realm of music information retrieval, similarity-based retrieval and auto-tagging serve as essential components. Given the limitations and non-scalability of human supervision signals, it becomes crucial for models to learn from…

Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. However, deep learning algorithms are sensitive to input data, and…

Unsupervised anomalous sound detection (ASD) aims to identify anomalous sounds by learning the features of normal operational sounds and sensing their deviations. Recent approaches have focused on the self-supervised task utilizing the…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

Despite its widespread adoption as the prominent neural architecture, the Transformer has spurred several independent lines of work to address its limitations. One such approach is selective state space models, which have demonstrated…

Depression detection research has increased over the last few decades, one major bottleneck of which is the limited data availability and representation learning. Recently, self-supervised learning has seen success in pretraining text…

Recent advances in audio declipping have substantially improved the state of the art.% in certain saturation regimes. Yet, practitioners need guidelines to choose a method, and while existing benchmarks have been instrumental in advancing…

Reliably modeling normality and differentiating abnormal appearances from normal cases is a very appealing approach for detecting pathologies in medical images. A plethora of such unsupervised anomaly detection approaches has been made in…

Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic features with clear physical meaning, these embeddings lack…

Recently proposed techniques for semi-supervised learning such as Temporal Ensembling and Mean Teacher have achieved state-of-the-art results in many important classification benchmarks. In this work, we expand the Mean Teacher approach to…

Universal sound separation (USS) is a task of separating mixtures of arbitrary sound sources. Typically, universal separation models are trained from scratch in a supervised manner, using labeled data. Self-supervised learning (SSL) is an…

Deep metric learning (DML) is a popular approach for images retrieval, solving verification (same or not) problems and addressing open set classification. Arguably, the most common DML approach is with triplet loss, despite significant…

The paper introduces Supervised Embedding and Clustering Anomaly Detection (SEMC-AD), a method designed to efficiently identify faulty alarm logs in a mobile network and alleviate the challenges of manual monitoring caused by the growing…

Unsupervised embedding learning aims to extract good representation from data without the need for any manual labels, which has been a critical challenge in many supervised learning tasks. This paper proposes a new unsupervised embedding…

Deep clustering is a deep neural network-based speech separation algorithm that first trains the mixed component of signals with high-dimensional embeddings, and then uses a clustering algorithm to separate each mixture of sources. In this…

In settings where only unlabelled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. A similar problem is faced when modelling infant language…