Acoustic Scene Classification for Bone-Conducted Sound Using Transfer Learning and Feature Fusion

Sijun Bi, Liang Xu, Shenghui Zhao*, Jing Wang

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

The air-conducted (AC) sound is usually used in the task of acoustic scene classification (ASC). Compared with the AC sound, bone-conducted (BC) sound has the unique advantage of shielding background noise. However, the amount of information contained in BC sound is far less than that in the AC sound due to its limited frequency bandwidth. In this paper, an acoustic scene classification method for BC sound is proposed with a small BC dataset. Firstly, the prosodic features are combined with the spectral features to capture more information, and feature fusion is adopted. Secondly, in order to deal with the small BC dataset, transfer learning is used with a large AC dataset. Finally, a deep learning network based on local residual learning is proposed. The experimental results show that the proposed method achieves the superior performance over the reference models.

Original languageEnglish
Title of host publication2022 5th International Conference on Information Communication and Signal Processing, ICICSP 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages519-522
Number of pages4
ISBN (Electronic)9781665485890
DOIs
Publication statusPublished - 2022
Event5th International Conference on Information Communication and Signal Processing, ICICSP 2022 - Shenzhen, China
Duration: 26 Nov 202228 Nov 2022

Publication series

Name2022 5th International Conference on Information Communication and Signal Processing, ICICSP 2022

Conference

Conference5th International Conference on Information Communication and Signal Processing, ICICSP 2022
Country/TerritoryChina
CityShenzhen
Period26/11/2228/11/22

Keywords

  • Bone-conducted sound
  • feature fusion
  • transfer learning

Fingerprint

Dive into the research topics of 'Acoustic Scene Classification for Bone-Conducted Sound Using Transfer Learning and Feature Fusion'. Together they form a unique fingerprint.

Cite this