SVD-based channel pruning for convolutional neural network in acoustic scene classification model

Jun Wang, Shengchen Li, Wenwu Wang

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

6 Citations (Scopus)

Abstract

Convolutional Neural Network (CNN) offers promising performance in Acoustic Scene Classification (ASC) tasks. The CNN model, however, often involves a large number of parameters, and thus requires large storage space for the implementation of the model. In this paper, we propose a new method for model pruning based on singular value decomposition (SVD). More specifically, the number of parameters is reduced by a low-rank decomposition method, where a matrix is decomposed into products of three small matrices. As a result, the original convolutional layer is decomposed into three smaller convolutional layers resulting in an overall reduction in the number of parameters involved in the model. The proposed method is evaluated on the dataset of ASC task in DCASE2018. The results illustrate that the proposed approach dramatically reduces the CNN layers size by more than 90% with relatively 1% performance loss and the activity of parameters in convolutional layers increases with performance loss of the compressed model.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages390-395
Number of pages6
ISBN (Electronic)9781538692141
DOIs
Publication statusPublished - Jul 2019
Externally publishedYes
Event2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019 - Shanghai, China
Duration: 8 Jul 201912 Jul 2019

Publication series

NameProceedings - 2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019

Conference

Conference2019 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2019
Country/TerritoryChina
CityShanghai
Period8/07/1912/07/19

Keywords

  • Compression
  • Convolutional Neural Network
  • Singular value decomposition

Cite this