Related papers: A Light-Weight Multimodal Framework for Improved E…

Jointly learning from a small labeled set and a larger unlabeled set is an active research topic under semi-supervised learning (SSL). In this paper, we propose a novel SSL method based on a two-stage framework for leveraging a large…

Environmental audio tagging is a newly proposed task to predict the presence or absence of a specific audio event in a chunk. Deep neural network (DNN) based methods have been successfully adopted for predicting the audio tags in the…

Annotating time boundaries of sound events is labor-intensive, limiting the scalability of strongly supervised learning in audio detection. To reduce annotation costs, weakly-supervised learning with only clip-level labels has been widely…

Acoustic event detection is essential for content analysis and description of multimedia recordings. The majority of current literature on the topic learns the detectors through fully-supervised techniques employing strongly labeled data.…

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…

In this technique report, we present a bunch of methods for the task 4 of Detection and Classification of Acoustic Scenes and Events 2017 (DCASE2017) challenge. This task evaluates systems for the large-scale detection of sound events using…

Weakly labeled datasets such as AudioSet have driven recent progress in audio tagging. However, annotation quality varies across sound classes. Labels may be incomplete, ambiguous, or unreliable, which introduces class-dependent supervision…

Pronounced as "musician", the musicnn library contains a set of pre-trained musically motivated convolutional neural networks for music audio tagging: https://github.com/jordipons/musicnn. This repository also includes some pre-trained…

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…

The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect…

AudioSet is a widely used benchmark in the audio research community and has significantly advanced various audio-related tasks. However, persistent issues with label accuracy and completeness remain critical bottlenecks that limit…

Multimodal pre-training for audio-and-text has recently been proved to be effective and has significantly improved the performance of many downstream speech understanding tasks. However, these state-of-the-art pre-training audio-text models…

In this paper, we describe our contribution to Task 2 of the DCASE 2018 Audio Challenge. While it has become ubiquitous to utilize an ensemble of machine learning methods for classification tasks to obtain better predictive performance, the…

In this paper, we present a gated convolutional neural network and a temporal attention-based localization method for audio classification, which won the 1st place in the large-scale weakly supervised sound event detection task of Detection…

Multimodal sentiment analysis aims to effectively integrate information from various sources to infer sentiment, where in many cases there are no annotations for unimodal labels. Therefore, most works rely on multimodal labels for training.…

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…

Audio tagging aims at predicting sound events occurred in a recording. Traditional models require enormous laborious annotations, otherwise performance degeneration will be the norm. Therefore, we investigate robust audio tagging models in…

Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Weakly Supervised Sound Event Detection (WSSED), which relies on audio tags without precise onset and offset times, has become prevalent due to the scarcity of strongly labeled data that includes exact temporal boundaries for events. This…