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/

Global: Zendy Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

For learning-based sound event localization and detection (SELD) methods,different acoustic environments in the training and test sets may result inlarge performance differences in the validation and evaluation stages.Different environments, such as different sizes of rooms, differentreverberation times, and different background noise, may be reasons for alearning-based system to fail. On the other hand, acquiring annotated spatialsound event samples, which include onset and offset time stamps, class types ofsound events, and direction-of-arrival (DOA) of sound sources is veryexpensive. In addition, deploying a SELD system in a new environment oftenposes challenges due to time-consuming training and fine-tuning processes. Toaddress these issues, we propose Meta-SELD, which applies meta-learning methodsto achieve fast adaptation to new environments. More specifically, based onModel Agnostic Meta-Learning (MAML), the proposed Meta-SELD aims to find goodmeta-initialized parameters to adapt to new environments with only a smallnumber of samples and parameter updating iterations. We can then quickly adaptthe meta-trained SELD model to unseen environments. Our experiments comparefine-tuning methods from pre-trained SELD models with our Meta-SELD on theSony-TAU Realistic Spatial Soundscapes 2023 (STARSSS23) dataset. The evaluationresults demonstrate the effectiveness of Meta-SELD when adapting to newenvironments.

META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection