Related papers: From Weak to Strong Sound Event Labels using Adapt…
Machine learning techniques applied to the Natural Language Processing (NLP) component of conversational agent development show promising results for improved accuracy and quality of feedback that a conversational agent can provide. The…
We tackle the task of environmental event classification by drawing inspiration from the transformer neural network architecture used in machine translation. We modify this attention-based feedforward structure in such a way that allows the…
Sequential sensor data is generated in a wide variety of practical applications. A fundamental challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent…
Sound event detection is a challenging task, especially for scenes with multiple simultaneous events. While event classification methods tend to be fairly accurate, event localization presents additional challenges, especially when large…
Sound event detection (SED) is typically posed as a supervised learning problem requiring training data with strong temporal labels of sound events. However, the production of datasets with strong labels normally requires unaffordable labor…
This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from…
Audio Event Detection is an important task for content analysis of multimedia data. Most of the current works on detection of audio events is driven through supervised learning approaches. We propose a weakly supervised learning framework…
Accurate labels are critical for deriving robust machine learning models. Labels are used to train supervised learning models and to evaluate most machine learning paradigms. In this paper, we model the accuracy and cost of a common weak…
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…
Strong labels are a necessity for evaluation of sound event detection methods, but often scarcely available due to the high resources required by the annotation task. We present a method for estimating strong labels using crowdsourced weak…
State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…
In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for sound events which aims to remove human supervision altogether…
Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In…
In this paper, we present a gated convolutional recurrent neural network based approach to solve task 4, large-scale weakly labelled semi-supervised sound event detection in domestic environments, of the DCASE 2018 challenge. Gated linear…
In this work we propose approaches to effectively transfer knowledge from weakly labeled web audio data. We first describe a convolutional neural network (CNN) based framework for sound event detection and classification using weakly…
In this paper, we propose a multi-level attention model to solve the weakly labelled audio classification problem. The objective of audio classification is to predict the presence or absence of audio events in an audio clip. Recently,…
Sound event detection (SED) is a task to detect sound events in an audio recording. One challenge of the SED task is that many datasets such as the Detection and Classification of Acoustic Scenes and Events (DCASE) datasets are weakly…
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets. However, it can be extremely time-consuming and prohibitively…
Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Global noise…
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for…