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

Huang Xie*, Okko Räsänen, Tuomas Virtanen

*Corresponding author for this work

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

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, ICASSP 2021
PublisherIEEE
Pages326-330
Number of pages5
Volume2021-June
ISBN (Electronic)978-1-7281-7605-5
DOIs
Publication statusPublished - 2021
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Acoustics, Speech, and Signal Processing - Virtua, Online, Toronto, Canada
Duration: 6 Jun 202111 Jun 2021

Publication series

NameProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP
Country/TerritoryCanada
CityToronto
Period06/06/202111/06/2021

Keywords

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

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