Abstract
Due to various factors, the vast majority of the research in the
field of Acoustic Scene Classification has used monaural or binaural
datasets. This paper introduces EigenScape - a new dataset
of 4th-order Ambisonic acoustic scene recordings - and presents
preliminary analysis of this dataset. The data is classified using a
standard Mel-Frequency Cepstral Coefficient - Gaussian Mixture
Model system, and the performance of this system is compared to
that of a new system using spatial features extracted using Directional
Audio Coding (DirAC) techniques. The DirAC features are
shown to perform well in scene classification, with some subsets
of these features outperforming the MFCC classification. The differences
in label confusion between the two systems are especially
interesting, as these suggest that certain scenes that are spectrally
similar might not necessarily be spatially similar.
field of Acoustic Scene Classification has used monaural or binaural
datasets. This paper introduces EigenScape - a new dataset
of 4th-order Ambisonic acoustic scene recordings - and presents
preliminary analysis of this dataset. The data is classified using a
standard Mel-Frequency Cepstral Coefficient - Gaussian Mixture
Model system, and the performance of this system is compared to
that of a new system using spatial features extracted using Directional
Audio Coding (DirAC) techniques. The DirAC features are
shown to perform well in scene classification, with some subsets
of these features outperforming the MFCC classification. The differences
in label confusion between the two systems are especially
interesting, as these suggest that certain scenes that are spectrally
similar might not necessarily be spatially similar.
| Original language | English |
|---|---|
| Pages | 42-45 |
| Number of pages | 4 |
| Publication status | Published - 16 Nov 2017 |
| Event | 2017 Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE2017), - Munich, Germany Duration: 16 Nov 2017 → 17 Jan 2018 http://www.cs.tut.fi/sgn/arg/dcase2017/workshop/ |
Conference
| Conference | 2017 Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE2017), |
|---|---|
| Country/Territory | Germany |
| City | Munich |
| Period | 16/11/17 → 17/01/18 |
| Internet address |
Keywords
- Acoustic scene classification
- ambisonics
- soundscape
Datasets
-
EigenScape: A Database of Spatial Acoustic Scene Recordings
Green, M. C. (Creator) & Murphy, D. T. (Supervisor), Zenodo, 22 Nov 2017
Dataset
-
EigenScape: A Database of Spatial Acoustic Scene Recordings (Raw Data)
Green, M. (Creator) & Murphy, D. T. (Supervisor), University of York, 31 May 2021
DOI: 10.15124/eaeaac50-483e-408f-a391-01b02d4ff9c4, https://webfiles.york.ac.uk/INFODATA/eaeaac50-483e-408f-a391-01b02d4ff9c4 and one more link, https://creativecommons.org/licenses/by/4.0/ (show fewer)
Dataset
-