Abstract
Acoustic scene classification (ASC) using front-end time-frequency features and back-end neural network classifiers has demonstrated good performance in recent years. However
a profusion of systems has arisen to suit different tasks anddatasets, utilising different feature and classifier types. This paper aims at a robust framework that can explore and utilise a
range of different time-frequency features and neural networks, either singly or merged, to achieve good classification performance. In particular, we exploit three different types of front-end time-frequency feature; log energy Mel filter, Gammatone filter and constant Q transform. At the back-end we evaluate effective a two-stage model that exploits a Convolutional
Neural Network for pre-trained feature extraction, followed by Deep Neural Network classifiers as a post-trained feature adap-
tation model and classifier. We also explore the use of a data augmentation technique for these features that effectively generates a variety of intermediate data, reinforcing model learning abilities, particularly for marginal cases. We assess performance on the DCASE2016 dataset, demonstrating good classification accuracies exceeding 90%, significantly outperforming
the DCASE2016 baseline and highly competitive compared to state-of-the-art systems.
a profusion of systems has arisen to suit different tasks anddatasets, utilising different feature and classifier types. This paper aims at a robust framework that can explore and utilise a
range of different time-frequency features and neural networks, either singly or merged, to achieve good classification performance. In particular, we exploit three different types of front-end time-frequency feature; log energy Mel filter, Gammatone filter and constant Q transform. At the back-end we evaluate effective a two-stage model that exploits a Convolutional
Neural Network for pre-trained feature extraction, followed by Deep Neural Network classifiers as a post-trained feature adap-
tation model and classifier. We also explore the use of a data augmentation technique for these features that effectively generates a variety of intermediate data, reinforcing model learning abilities, particularly for marginal cases. We assess performance on the DCASE2016 dataset, demonstrating good classification accuracies exceeding 90%, significantly outperforming
the DCASE2016 baseline and highly competitive compared to state-of-the-art systems.
Original language | English |
---|---|
Title of host publication | INTERSPEECH 2019 |
Pages | 3634-3638 |
DOIs | |
Publication status | Published - Sept 2019 |
Event | Interspeech 2019 - Graz, Austria Duration: 15 Sept 2019 → 19 Sept 2019 |
Conference
Conference | Interspeech 2019 |
---|---|
Country/Territory | Austria |
City | Graz |
Period | 15/09/19 → 19/09/19 |
Research Field
- Former Research Field - Data Science