Related papers: Pseudo Strong Labels from Frame-Level Predictions …
Sound event detection (SED) entails identifying the type of sound and estimating its temporal boundaries from acoustic signals. These events are uniquely characterized by their spatio-temporal features, which are determined by the way they…
Solving real-world problems, particularly with deep learning, relies on the availability of abundant, quality data. In this paper we develop a novel framework that maximises the utility of time-series datasets that contain only small…
Despite recent progress in large-scale sound event detection (SED) systems capable of handling hundreds of sound classes, existing multi-class classification frameworks remain fundamentally limited. They cannot process free-text sound…
A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn…
Weakly labelled audio tagging aims to predict the classes of sound events within an audio clip, where the onset and offset times of the sound events are not provided. Previous works have used the multiple instance learning (MIL) framework,…
While fine-tuning pre-trained networks has become a popular way to train image segmentation models, such backbone networks for image segmentation are frequently pre-trained using image classification source datasets, e.g., ImageNet. Though…
The rapid development of deep learning has driven significant progress in image semantic segmentation - a fundamental task in computer vision. Semantic segmentation algorithms often depend on the availability of pixel-level labels (i.e.,…
Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances…
Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…
Compared to conventional semantic segmentation with pixel-level supervision, Weakly Supervised Semantic Segmentation (WSSS) with image-level labels poses the challenge that it always focuses on the most discriminative regions, resulting in…
In this paper, we propose a deep-learning framework for environmental sound deepfake detection (ESDD) -- the task of identifying whether the sound scene and sound event in an input audio recording is fake or not. To this end, we conducted…
While multitask and transfer learning has shown to improve the performance of neural networks in limited data settings, they require pretraining of the model on large datasets beforehand. In this paper, we focus on improving the performance…
The development of audio event recognition systems require labeled training data, which are generally hard to obtain. One promising source of recordings of audio events is the large amount of multimedia data on the web. In particular, if…
Speech enhancement is a task to improve the intelligibility and perceptual quality of degraded speech signal. Recently, neural networks based methods have been applied to speech enhancement. However, many neural network based methods…
This paper presents our work of training acoustic event detection (AED) models using unlabeled dataset. Recent acoustic event detectors are based on large-scale neural networks, which are typically trained with huge amounts of labeled data.…
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…
This report proposes a polyphonic sound event detection (SED) method for the DCASE 2020 Challenge Task 4. The proposed SED method is based on semi-supervised learning to deal with the different combination of training datasets such as…
The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…
The study of label noise in sound event recognition has recently gained attention with the advent of larger and noisier datasets. This work addresses the problem of missing labels, one of the big weaknesses of large audio datasets, and one…
Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing…