Related papers: Audio Set classification with attention model: A p…

Traditional supervised learning tasks require a label for every instance in the training set, but in many real-world applications, labels are only available for collections (bags) of instances. This problem setting, known as multiple…

Categorical speech emotion recognition is typically performed as a sequence-to-label problem, i.e., to determine the discrete emotion label of the input utterance as a whole. One of the main challenges in practice is that most of the…

We present a probabilistic modeling and inference framework for discriminative analysis dictionary learning under a weak supervision setting. Dictionary learning approaches have been widely used for tasks such as low-level signal denoising…

Sound event detection (SED) methods are tasked with labeling segments of audio recordings by the presence of active sound sources. SED is typically posed as a supervised machine learning problem, requiring strong annotations for the…

Considering that acoustic scenes and sound events are closely related to each other, in some previous papers, a joint analysis of acoustic scenes and sound events utilizing multitask learning (MTL)-based neural networks was proposed. In…

In this paper, we introduce a new problem, named audio-visual video parsing, which aims to parse a video into temporal event segments and label them as either audible, visible, or both. Such a problem is essential for a complete…

Labeling data for classification requires significant human effort. To reduce labeling cost, instead of labeling every instance, a group of instances (bag) is labeled by a single bag label. Computer algorithms are then used to infer the…

This paper proposes a neural network architecture and training scheme to learn the start and end time of sound events (strong labels) in an audio recording given just the list of sound events existing in the audio without time information…

Curating datasets that span multiple languages is challenging. To make the collection more scalable, researchers often incorporate one or more imperfect classifiers in the process, like language identification models. These models, however,…

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…

We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised…

Acoustic Scene Classification (ASC) and Sound Event Detection (SED) are two separate tasks in the field of computational sound scene analysis. In this work, we present a new dataset with both sound scene and sound event labels and use this…

Audiological datasets contain valuable knowledge about hearing loss in patients, which can be uncovered using data-driven, federated learning techniques. Our previous approach summarized patient information from one audiological dataset…

The performances of Sound Event Detection (SED) systems are greatly limited by the difficulty in generating large strongly labeled dataset. In this work, we used two main approaches to overcome the lack of strongly labeled data. First, we…

To reveal the importance of temporal precision in ground truth audio event labels, we collected precise (~0.1 sec resolution) "strong" labels for a portion of the AudioSet dataset. We devised a temporally strong evaluation set (including…

Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels are available. MIL has a variety of…

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…

Weakly-supervised action localization requires training a model to localize the action segments in the video given only video level action label. It can be solved under the Multiple Instance Learning (MIL) framework, where a bag (video)…

Multiple instance learning (MIL) is concerned with learning from sets (bags) of objects (instances), where the individual instance labels are ambiguous. In this setting, supervised learning cannot be applied directly. Often, specialized MIL…

The design of new methods and models when only weakly-labeled data are available is of paramount importance in order to reduce the costs of manual annotation and the considerable human effort associated with it. In this work, we address…