paper-with-me

홈 › Papers

Sound Event Bounding Boxes

2024-06-06 · Janek Ebbers, Francois G. Germain, Gordon Wichern, Jonathan Le Roux

Sound event detection is the task of recognizing sounds and determining their extent (onset/offset times) within an audio clip. Existing systems commonly predict sound presence confidence in short time frames. Then, thresholding produces binary frame-level presence decisions, with the extent of individual events determined by merging consecutive positive frames. In this paper, we show that frame-level thresholding degrades the prediction of the event extent by coupling it with the system's sound presence confidence. We propose to decouple the prediction of event extent and confidence by introducing SEBBs, which format each sound event prediction as a tuple of a class type, extent, and overall confidence. We also propose a change-detection-based algorithm to convert legacy frame-level outputs into SEBBs. We find the algorithm significantly improves the performance of DCASE 2023 Challenge systems, boosting the state of the art from .644 to .686 PSDS1.

📄 PDF Abstract BibTeX arXiv:2406.04212

Code (1)

merlresearch/sebbs 공식 구현

Tasks

Change DetectionEvent DetectionPredictionSound Event Detection

Similar Papers 제목 키워드 기반

Self Training and Ensembling Frequency Dependent Networks with Coarse Prediction Pooling and Sound Event Bounding Boxes

2024-06-22 · Hyeonuk Nam, Deokki Min, Seungdeok Choi, Inhan Choi 외

To tackle sound event detection (SED), we propose frequency dependent networks (FreDNets), which heavily leverage frequency-dependent methods. We apply frequency warping and FilterAugment, which are frequency-dependent d…

Change DetectionData AugmentationEvent DetectionPseudo Label+1

The Sound of Bounding-Boxes

2022-03-30 · Takashi Oya, Shohei Iwase, Shigeo Morishima

In the task of audio-visual sound source separation, which leverages visual information for sound source separation, identifying objects in an image is a crucial step prior to separating the sound source. However, existi…

Exploring the Potential of SSL Models for Sound Event Detection

2025-05-17 · Hanfang Cui, Longfei Song, Li Li, Dongxing Xu 외

Self-supervised learning (SSL) models offer powerful representations for sound event detection (SED), yet their synergistic potential remains underexplored. This study systematically evaluates state-of-the-art SSL models…

Event DetectionModel SelectionSelf-Supervised LearningSound Event Detection

Fusion of Audio and Visual Embeddings for Sound Event Localization and Detection

2023-12-14 · Davide Berghi, Peipei Wu, Jinzheng Zhao, Wenwu Wang 외

Sound event localization and detection (SELD) combines two subtasks: sound event detection (SED) and direction of arrival (DOA) estimation. SELD is usually tackled as an audio-only problem, but visual information has bee…

Data AugmentationEvent DetectionSound Event DetectionSound Event Localization and Detection

Semantic Segmentation and Object Detection Towards Instance Segmentation: Breast Tumor Identification

2021-08-06 · Mohamed Mejri, Aymen Mejri, Oumayma Mejri, Chiraz Fekih

Breast cancer is one of the factors that cause the increase of mortality of women. The most widely used method for diagnosing this geological disease i.e. breast cancer is the ultrasound scan. Several key features such a…

DecoderInstance Segmentationobject-detectionObject Detection+2