Sound Event Detection by Pseudo-Labeling in Weakly Labeled Dataset

Weakly labeled sound event detection (WSED) is an important task as it can facilitate the data collection efforts before constructing a strongly labeled sound event dataset. Recent high performance in deep learning-based WSED’s exploited using a segmentation mask for detecting the target feature map...

Descripción completa

Detalles Bibliográficos
Autores principales: Park, Chungho, Kim, Donghyeon, Ko, Hanseok
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8705589/
https://www.ncbi.nlm.nih.gov/pubmed/34960475
http://dx.doi.org/10.3390/s21248375

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8705589/
https://www.ncbi.nlm.nih.gov/pubmed/34960475
http://dx.doi.org/10.3390/s21248375

Ejemplares similares