English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In this paper, we propose a domain adaptation framework to address the devicemismatch issue in acoustic scene classification leveraging upon neural labelembedding (NLE) and relational teacher student learning (RTSL). Taking intoaccount the structural relationships between acoustic scene classes, ourproposed framework captures such relationships which are intrinsicallydevice-independent. In the training stage, transferable knowledge is condensedin NLE from the source domain. Next in the adaptation stage, a novel RTSLstrategy is adopted to learn adapted target models without using pairedsource-target data often required in conventional teacher student learning. Theproposed framework is evaluated on the DCASE 2018 Task1b data set. Experimentalresults based on AlexNet-L deep classification models confirm the effectivenessof our proposed approach for mismatch situations. NLE-alone adaptation comparesfavourably with the conventional device adaptation and teacher student basedadaptation techniques. NLE with RTSL further improves the classificationaccuracy.

Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification