Related papers: Hierarchical Label Propagation: A Model-Size-Depen…
Audio tagging is an active research area and has a wide range of applications. Since the release of AudioSet, great progress has been made in advancing model performance, which mostly comes from the development of novel model architectures…
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…
Learning with noisy labels in multimedia classification often combines external annotations and model predictions into a single reliability weight, even though the two sources can fail for different reasons. We instead estimate disentangled…
Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We…
Audio classification is the task of identifying the sound categories that are associated with a given audio signal. This paper presents an investigation on large-scale audio classification based on the recently released AudioSet database.…
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…
Most audio tagging models are trained with one-hot labels as supervised information. However, one-hot labels treat all sound events equally, ignoring the semantic hierarchy and proximity relationships between sound events. In contrast, the…
Large-scale audio tagging datasets inevitably contain imperfect labels, such as clip-wise annotated (temporally weak) tags with no exact on- and offsets, due to a high manual labeling cost. This work proposes pseudo strong labels (PSL), a…
Machine listening systems often rely on fixed taxonomies to organize and label audio data, key for training and evaluating deep neural networks (DNNs) and other supervised algorithms. However, such taxonomies face significant constraints:…
Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require…
While existing hierarchical text classification (HTC) methods attempt to capture label hierarchies for model training, they either make local decisions regarding each label or completely ignore the hierarchy information during inference. To…
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…
As sound event classification moves towards larger datasets, issues of label noise become inevitable. Web sites can supply large volumes of user-contributed audio and metadata, but inferring labels from this metadata introduces errors due…
Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing…
While deep learning has been incredibly successful in modeling tasks with large, carefully curated labeled datasets, its application to problems with limited labeled data remains a challenge. The aim of the present work is to improve the…
Hierarchical text classification (HTC) is a challenging subtask of multi-label classification due to its complex label hierarchy. Recently, the pretrained language models (PLM)have been widely adopted in HTC through a fine-tuning paradigm.…
The success of deep learning requires high-quality annotated and massive data. However, the size and the quality of a dataset are usually a trade-off in practice, as data collection and cleaning are expensive and time-consuming. In…
Supervised machine learning frameworks rely on extensive labeled datasets for robust performance on real-world tasks. However, there is a lack of large annotated datasets in audio and music domains, as annotating such recordings is…
Labeling and maintaining a commercial sound effects library is a time-consuming task exacerbated by databases that continually grow in size and undergo taxonomy updates. Moreover, sound search and taxonomy creation are complicated by…
This paper addresses performance degradation in anomalous sound detection (ASD) when neither sufficiently similar machine data nor operational state labels are available. We present an integrated pipeline that combines three complementary…