End-to-end Convolutional Neural Networks for Sound Event Detection in Urban Environments
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 ?lter bank, followed by a 2D...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
FRUCT
2019-04-01
|
| Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| Subjects: | |
| Online Access: | https://fruct.org/publications/fruct24/files/Zin.pdf
|
| Summary: | 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 ?lter bank, followed by a 2D CNN for the classi?cation task. The main goal of this two-stage architecture is to bring more interpretability to the ?rst 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 normaliza- tion, 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 modi?es the ?lter bank as well as the PCEN normalization parameters. The obtained system achieves classi?cation results that are comparable to the state-of-the-art, while decreasing the number of parameters involved. |
|---|---|
| ISSN: | 2305-7254 2343-0737 |