Acoustic scene classification using higher-order ambisonic features

TY - GEN

T1 - Acoustic scene classification using higher-order ambisonic features

AU - Green, Marc C.

AU - Adavanne, Sharath

AU - Murphy, Damian

AU - Virtanen, Tuomas

N1 - Funding Information: †The research leading to these results has received funding from the European Research Council under the European Union’s H2020 Framework Program through ERC Grant Agreement 637422 EVERYSOUND. The authors also wish to acknowledge CSC-IT Center for Science, Finland, for computational resources. Funding Information: ∗Funding was provided by a UK Engineering and Physical Sciences Research Council (EPSRC) Doctoral Training Award, an Audio Engineering Society (AES) Educational Foundation grant, and the Department of Electronic Engineering at the University of York. Publisher Copyright: © 2019 IEEE.

PY - 2019/12/23

Y1 - 2019/12/23

N2 - This paper investigates the potential of using higher-order Ambisonic features to perform acoustic scene classification. We compare the performance of systems trained using first-order and fourth-order spatial features extracted from the EigenScape database. Using both Gaussian mixture model and convolutional neural network classifiers, we show that features extracted from higher-order Ambisonics can yield increased classification accuracies relative to first-order features. Diffuseness-based features seem to describe scenes particularly well relative to direction-of-arrival based features. With specific feature subsets, however, differences in classification accuracy between first and fourth-order features become negligible.

AB - This paper investigates the potential of using higher-order Ambisonic features to perform acoustic scene classification. We compare the performance of systems trained using first-order and fourth-order spatial features extracted from the EigenScape database. Using both Gaussian mixture model and convolutional neural network classifiers, we show that features extracted from higher-order Ambisonics can yield increased classification accuracies relative to first-order features. Diffuseness-based features seem to describe scenes particularly well relative to direction-of-arrival based features. With specific feature subsets, however, differences in classification accuracy between first and fourth-order features become negligible.

KW - acoustic scene classification

KW - ambisonics

KW - convolutional neural networks

KW - gaussian mixture models

KW - spatial audio

UR - http://www.scopus.com/inward/record.url?scp=85077990714&partnerID=8YFLogxK

U2 - 10.1109/WASPAA.2019.8937282

DO - 10.1109/WASPAA.2019.8937282

M3 - Conference contribution

AN - SCOPUS:85077990714

T3 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics

SP - 328

EP - 332

BT - 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019

PB - IEEE

T2 - 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019

Y2 - 20 October 2019 through 23 October 2019

ER -