Skip to main content
Top

2019 | OriginalPaper | Chapter

A Comparison of Attention Mechanisms of Convolutional Neural Network in Weakly Labeled Audio Tagging

Authors : Yuanbo Hou, Qiuqiang Kong, Shengchen Li

Published in: Proceedings of the 6th Conference on Sound and Music Technology (CSMT)

Publisher: Springer Singapore

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Audio tagging aims to predict the types of sound events occurring in audio clips. Recently, the convolutional recurrent neural network (CRNN) has achieved state-of-the-art performance in audio tagging. In CRNN, convolutional layers are applied on input audio features to extract high-level representations followed by recurrent layers. To better learn high-level representations of acoustic features, attention mechanisms were introduced to the convolutional layers of CRNN. Attention is a learning technique that could steer the model to information important to the task to obtain better performance. The two different attention mechanisms in the CRNN, the Squeeze-and-Excitation (SE) block and gated linear unit (GLU), are based on a gating mechanism, but their concerns are different. To compare the performance of the SE block and GLU, we propose to use a CRNN with a SE block (SE-CRNN) and a CRNN with a GLU (GLU-CRNN) in weakly labeled audio tagging and compare these results with the CRNN baseline. The experiments show that the GLU-CRNN achieves an area under curve score of 0.877 in polyphonic audio tagging, outperforming the SE-CRNN of 0.865 and the CRNN baseline of 0.838. The results show that the performance of attention based on GLU is better than the performance of attention based on the SE block in CRNN for weakly labeled polyphonic audio tagging.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Literature
1.
go back to reference Xu Y, Kong Q, Wang W, Plumbley MD (2018) Large-scale weakly supervised audio classification using gatedconvolutional neural network. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018, Calgary Canada, 2018, (pp 121–125) Xu Y, Kong Q, Wang W, Plumbley MD (2018) Large-scale weakly supervised audio classification using gatedconvolutional neural network. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018, Calgary Canada, 2018, (pp 121–125)
2.
go back to reference Stowell D, Giannoulis D, Benetos E, Lagrange M, Plumbley MD (2015) Detection and classification of acoustic scenes and events. IEEE Trans Multimed 17(10):1733–1746CrossRef Stowell D, Giannoulis D, Benetos E, Lagrange M, Plumbley MD (2015) Detection and classification of acoustic scenes and events. IEEE Trans Multimed 17(10):1733–1746CrossRef
3.
go back to reference Dimitrov S, Britz J, Brandherm B, Frey J (2014) Analyzing sounds of home environment for device recognition. In: European Conference on Ambient Intelligence, pp 1–16 Dimitrov S, Britz J, Brandherm B, Frey J (2014) Analyzing sounds of home environment for device recognition. In: European Conference on Ambient Intelligence, pp 1–16
4.
go back to reference Kumar A, Raj B (2016) Audio event detection using weakly labeled data. In: ACM on Multimedia Conference, pp 1038–1047 Kumar A, Raj B (2016) Audio event detection using weakly labeled data. In: ACM on Multimedia Conference, pp 1038–1047
5.
go back to reference Mesaros A, Heittola T, Diment A, Elizalde B, Shah A, Vincent E, Raj B, Virtanen T (2017) DCASE 2017 challenge setup: Tasks, datasets and baseline system. In: Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE) 2017, Munich, Germany, 2017 Mesaros A, Heittola T, Diment A, Elizalde B, Shah A, Vincent E, Raj B, Virtanen T (2017) DCASE 2017 challenge setup: Tasks, datasets and baseline system. In: Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE) 2017, Munich, Germany, 2017
6.
go back to reference Dauphin YN, Fan A, Auli M, Grangier D (2017) Language modeling with gated convolutional networks. In: Proceedings of International Conference on Machine Learning (ICML), 2017, pp 933–941 Dauphin YN, Fan A, Auli M, Grangier D (2017) Language modeling with gated convolutional networks. In: Proceedings of International Conference on Machine Learning (ICML), 2017, pp 933–941
7.
go back to reference Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141 Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141
8.
go back to reference Mnih V, Heess N, Graves A (2014) Recurrent models of visual attention. In: Advances in neural information processing systems, pp 2204–2212 Mnih V, Heess N, Graves A (2014) Recurrent models of visual attention. In: Advances in neural information processing systems, pp 2204–2212
9.
go back to reference Mesaros A, Heittola T, Eronen A, Virtanen T (2010) Acoustic event detection in real life recordings. In: European Signal Processing Conference. IEEE, pp 1267–1271 Mesaros A, Heittola T, Eronen A, Virtanen T (2010) Acoustic event detection in real life recordings. In: European Signal Processing Conference. IEEE, pp 1267–1271
10.
go back to reference Lidy T, Schindler A (2016) CQT-based convolutional neural networks for audio scene classification: In: Proceedings of the detection and classification of acoustic scenes and events 2016 workshop 90:1032–1048 Lidy T, Schindler A (2016) CQT-based convolutional neural networks for audio scene classification: In: Proceedings of the detection and classification of acoustic scenes and events 2016 workshop 90:1032–1048
11.
go back to reference Krizhevsky A, Sutskever I, Hinton GE (2010) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105 Krizhevsky A, Sutskever I, Hinton GE (2010) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
12.
go back to reference Choi K, Fazekas G, Sandler M (2016) Automatic tagging using deep convolutional neural networks. In: arXiv preprint, arXiv:1606.00298 Choi K, Fazekas G, Sandler M (2016) Automatic tagging using deep convolutional neural networks. In: arXiv preprint, arXiv:1606.00298
13.
go back to reference Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp 1254–1259CrossRef Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp 1254–1259CrossRef
14.
go back to reference Xu Y, Kong Q, Huang Q, Wang W, Plumbley MD (2017) Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging. In: arXiv preprint, arXiv:1703.06052 Xu Y, Kong Q, Huang Q, Wang W, Plumbley MD (2017) Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging. In: arXiv preprint, arXiv:1703.06052
15.
go back to reference Xu Y, Huang Q, Wang W, Foster P, Sigtia S, Jackson PJ, Plumbley MD (2017) Unsupervised feature learning based on deep models for environmental audio tagging. In: IEEE/ACM Transactions Audio, Speech, Language Process 25(6):1230–1241CrossRef Xu Y, Huang Q, Wang W, Foster P, Sigtia S, Jackson PJ, Plumbley MD (2017) Unsupervised feature learning based on deep models for environmental audio tagging. In: IEEE/ACM Transactions Audio, Speech, Language Process 25(6):1230–1241CrossRef
16.
go back to reference Serizel R, Turpault N, Eghbal-Zadeh H (2018) Large-scale weakly labeled semi-supervised sound event detection in domestic environments. In Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE) 2018, November 2018, Surrey, UK Serizel R, Turpault N, Eghbal-Zadeh H (2018) Large-scale weakly labeled semi-supervised sound event detection in domestic environments. In Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE) 2018, November 2018, Surrey, UK
17.
go back to reference Mesaros A, Heittola T, Virtanen T (2016) Metrics for polyphonic sound event detection. Appl Sci 6(6):162CrossRef Mesaros A, Heittola T, Virtanen T (2016) Metrics for polyphonic sound event detection. Appl Sci 6(6):162CrossRef
18.
go back to reference Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29–36CrossRef Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1):29–36CrossRef
Metadata
Title
A Comparison of Attention Mechanisms of Convolutional Neural Network in Weakly Labeled Audio Tagging
Authors
Yuanbo Hou
Qiuqiang Kong
Shengchen Li
Copyright Year
2019
Publisher
Springer Singapore
DOI
https://doi.org/10.1007/978-981-13-8707-4_8