TY - GEN
T1 - Acoustic scene classification using kervolution-based subspectralnet
AU - Nandi, Ritika
AU - Shekhar, Shashank
AU - Mulimani, Manjunath
N1 - Publisher Copyright:
Copyright © 2021 ISCA.
PY - 2021
Y1 - 2021
N2 - In this paper, a Kervolution-based SubSpectralNet model is proposed for Acoustic Scene Classification (ASC). SubSpectralNet is a competitive model which divides the mel spectrogram into horizontal slices termed as sub-spectrograms that are considered as input to the Convolutional Neural Network (CNN). In this work, the linear convolutional operation of SubSpectralNet is replaced with a non-linear operation using the kernel trick. This is also known as kervolution (kernel convolution)-based SubSpectralNet. The performance of the proposed methodology is evaluated on the DCASE (Detection and Classification of Acoustic Scenes and Events) 2018 development dataset. The proposed method achieves 73.52% and 75.76% accuracy with Polynomial and Gaussian Kernels respectively.
AB - In this paper, a Kervolution-based SubSpectralNet model is proposed for Acoustic Scene Classification (ASC). SubSpectralNet is a competitive model which divides the mel spectrogram into horizontal slices termed as sub-spectrograms that are considered as input to the Convolutional Neural Network (CNN). In this work, the linear convolutional operation of SubSpectralNet is replaced with a non-linear operation using the kernel trick. This is also known as kervolution (kernel convolution)-based SubSpectralNet. The performance of the proposed methodology is evaluated on the DCASE (Detection and Classification of Acoustic Scenes and Events) 2018 development dataset. The proposed method achieves 73.52% and 75.76% accuracy with Polynomial and Gaussian Kernels respectively.
UR - http://www.scopus.com/inward/record.url?scp=85119497315&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119497315&partnerID=8YFLogxK
U2 - 10.21437/Interspeech.2021-656
DO - 10.21437/Interspeech.2021-656
M3 - Conference contribution
AN - SCOPUS:85119497315
T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
SP - 26
EP - 30
BT - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
PB - International Speech Communication Association
T2 - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Y2 - 30 August 2021 through 3 September 2021
ER -