Título:
End–to–end convolutional neural networks for sound event detection in urban environments.
Otros títulos:
Coordinador:
Director:
Compilador:
Autor:
Zinemanas, Pablo
Cancela, Pablo
Rocamora, Martín
Cancela, Pablo
Rocamora, Martín
Tutor:
Tipo de documento:
Ponencia
Editor:
Palabras clave:
Sound Event Detection (SED)
Convolutional Neural Networks (CNN)
Per Channel Energy Normalization (PCEN)
Convolutional Neural Networks (CNN)
Per Channel Energy Normalization (PCEN)
Descriptores:
Año de publicación:
2019
Contenido:
Resumen:
We present a novel approach to tackle the problem of sound event detection (SED) in urban environments using end-to-end convolutional neural networks (CNN). It consists of a 1D CNN for extracting the energy on mel–frequency bands from the audio signal based on a simple filter bank, followed by a 2D CNN for the classification task. The main goal of this two-stage architecture is to bring more interpretability to the first layers of the network and to permit their reutilization in other problems of same the domain. We present a novel model to calculate the mel–spectrogam using a neural network that outperforms an existing work, both in its simplicity and its matching performance. Also,we implement a recently proposed approach to normalize the energy of the mel–spectrogram (per channel energy normalization, PCEN) as a layer of the neural network. We show how the parameters of this normalization can be learned by the network and why this is useful for SED on urban environments. We study how the training modifies the filter bank as well as the PCEN normalization parameters. The obtained system achieves classification results that are comparable to the state–of–the–art, while decreasing the number of parameters involved
Descripción:
FRUCT Proceedings, vol. 24, no. 1.
metadata.articulos.dc.description.uri:
Editorial:
Open Innovations Association FRUCT
EN:
Proceedings of the 24th Conference of Open Innovations Association FRUCT, 2nd IEEE FRUCT International Workshop on Semantic Audio and the Internet of Things, Moscow, Russia, 8-12 apr. 2019, pp. 533--539.
Financiadores:
Citación:
Zinemanas, P., Cancela, P. y Rocamora, M. End–to–end convolutional neural networks for sound event detection in urban environments [en línea]. EN: Proceedings of the 24th Conference of Open Innovations Association FRUCT, 2nd IEEE FRUCT International Workshop on Semantic Audio and the Internet of Things, Moscow, Russia, 8-12 apr. 2019, pp. 533-539.
Citación:
metadata.articulos.cc.license.name:
ISBN:
e-ISBN:
ISSN:
2305-7254
ISMN:
Otros identificadores:
Cobertura geográfica:
Cobertura temporal:
Departamento académico:
Procesamiento de Señales
Grupo de investigación:
Procesamiento de Audio (GPA)
Licencia:
Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)
| Ficheros | Descripción | Tamaño | Formato | ||
|---|---|---|---|---|---|
| ZCR19.pdf | Versión publicada | 528.39 KB | Adobe PDF |