paper-with-me

Papers

An Ontology-Aware Framework for Audio Event Classification

2020-01-27 · Yiwei Sun, Shabnam Ghaffarzadegan

Recent advancements in audio event classification often ignore the structure and relation between the label classes available as prior information. This structure can be defined by ontology and augmented in the classifier as a form of domain knowledge. To capture such dependencies between the labels, we propose an ontology-aware neural network containing two components: feed-forward ontology layers and graph convolutional networks (GCN). The feed-forward ontology layers capture the intra-dependencies of labels between different levels of ontology. On the other hand, GCN mainly models inter-dependency structure of labels within an ontology level. The framework is evaluated on two benchmark datasets for single-label and multi-label audio event classification tasks. The results demonstrate the proposed solutions efficacy to capture and explore the ontology relations and improve the classification performance.

📄 PDF Abstract BibTeX arXiv:2001.10048

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classification

Methods 이 논문이 사용한 방법론

Graph Convolutional Networks 설명 없음
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Sound event classification using ontology-based neural networks

2018-10-23 · NIPS Workshop IRASL 2018 · Anonymous

State of the art sound event classification relies in neural networks to learn the associations between class labels and audio recordings within a dataset. These datasets typically define an ontology to create a structur…

Classification

Ontology-aware Learning and Evaluation for Audio Tagging

2022-11-22 · Haohe Liu, Qiuqiang Kong, Xubo Liu, Xinhao Mei 외

This study defines a new evaluation metric for audio tagging tasks to overcome the limitation of the conventional mean average precision (mAP) metric, which treats different kinds of sound as independent classes without …

Audio Tagging

Audio Question Answering with GRPO-Based Fine-Tuning and Calibrated Segment-Level Predictions

2025-11-18 · Marcel Gibier, Nolwenn Celton, Raphaël Duroselle, Pierre Serrano 외 arxiv

In this report, we describe our submission to Track 5 of the DCASE 2025 Challenge for the task of Audio Question Answering(AQA). Our system leverages the SSL backbone BEATs to extract frame-level audio features, which ar…

Question Answering

MMAudio-LABEL: Audio Event Labeling via Audio Generation for Silent Video

2026-05-01 · Kazuya Tateishi, Akira Takahashi, Atsuo Hiroe, Hirofumi Takeda 외 arxiv

Recent advances in multimodal generation have enabled high-quality audio generation from silent videos. Practical applications, such as sound production, demand not only the generated audio but also explicit sound event …

Sound Event Detectionmultimodal generationAudio Generation

Ontological Learning from Weak Labels

2022-03-04 · Larry Tang, Po Hao Chou, Yi Yu Zheng, Ziqian Ge 외

Ontologies encompass a formal representation of knowledge through the definition of concepts or properties of a domain, and the relationships between those concepts. In this work, we seek to investigate whether using thi…