Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections

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

13 Citations (Scopus)
10 Downloads (Pure)

Abstract

In this paper, we study zero-shot learning in audio classification through factored linear and nonlinear acoustic-semantic projections between audio instances and sound classes. Zero-shot learning in audio classification refers to classification problems that aim at recognizing audio instances of sound classes, which have no available training data but only semantic side information. In this paper, we address zero-shot learning by employing factored linear and nonlinear acoustic-semantic projections. We develop factored linear projections by applying rank decomposition to a bilinear model, and use nonlinear activation functions, such as tanh, to model the non-linearity between acoustic embeddings and semantic embeddings. Compared with the prior bilinear model, experimental results show that the proposed projection methods are effective for improving classification performance of zero-shot learning in audio classification.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Acoustics, Speech, and Signal Processing
Subtitle of host publicationICASSP 2021
PublisherIEEE
Pages326-330
Number of pages5
Volume2021-June
ISBN (Electronic)978-1-7281-7606-2
ISBN (Print)978-1-7281-7605-5
DOIs
Publication statusPublished - 2021
Publication typeA4 Article in conference proceedings
EventIEEE International Conference on Acoustics, Speech and Signal Processing -
Duration: 1 Jan 19001 Jan 2000

Publication series

NameProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN (Print)1520-6149

Conference

ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing
Period1/01/001/01/00

Keywords

  • Acoustic-semantic projection
  • Audio classification
  • Zero-shot learning

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Zero-shot audio classification with factored linear and nonlinear acoustic-semantic projections'. Together they form a unique fingerprint.

Cite this