Related papers: Power Pooling Operators and Confidence Learning fo…

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…

Speech evaluation measures a learners oral proficiency using automatic models. Corpora for training such models often pose sparsity challenges given that there often is limited scored data from teachers, in addition to the score…

Semi-supervised semantic segmentation (SSSS) aims to improve segmentation performance by utilizing large amounts of unlabeled data with limited labeled samples. Existing methods often suffer from coupling, where over-reliance on initial…

Sound Event Detection (SED) aims to predict the temporal boundaries of all the events of interest and their class labels, given an unconstrained audio sample. Taking either the splitand-classify (i.e., frame-level) strategy or the more…

Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…

Polyphonic sound event detection (polyphonic SED) is an interesting but challenging task due to the concurrence of multiple sound events. Recently, SED methods based on convolutional neural networks (CNN) and recurrent neural networks (RNN)…

Self-training is a well-known approach for semi-supervised learning. It consists of iteratively assigning pseudo-labels to unlabeled data for which the model is confident and treating them as labeled examples. For neural networks, softmax…

This technical report describes the systems submitted to the DCASE2022 challenge task 3: sound event localization and detection (SELD). The task aims to detect occurrences of sound events and specify their class, furthermore estimate their…

Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this…

Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show promise for robust SED by separating target events;…

The challenges of polyphonic sound event detection (PSED) stem from the detection of multiple overlapping events in a time series. Recent efforts exploit Deep Neural Networks (DNNs) on Time-Frequency Representations (TFRs) of audio clips as…

Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations. However, there has not been a rigorous evaluation regarding the…

This paper develops a novel machine learning-based framework using Semi-Supervised Multi-Task Learning (SS-MTL) for power system dynamic security assessment that is accurate, reliable, and aware of topological changes. The learning…

Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…

While Self-Supervised Learning has helped reap the benefit of the scale from the available unlabeled data, the learning paradigms are continuously being bettered. We present a new pre-training strategy named ccc-wav2vec 2.0, which uses…

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

Semi-supervised learning aims to leverage a large amount of unlabeled data for performance boosting. Existing works primarily focus on image classification. In this paper, we delve into semi-supervised learning for object detection, where…

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliablility of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an…

A novel semi-supervised learning technique is introduced based on a simple iterative learning cycle together with learned thresholding techniques and an ensemble decision support system. State-of-the-art model performance and increased…

Recent speaker verification studies have achieved notable success by leveraging layer-wise output from pre-trained Transformer models. However, few have explored the advancements in aggregating these multi-level features beyond the static…