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

This technical report presents the modeling approaches used in our submissionto the ICML Expressive Vocalizations Workshop & Competition multitask track(ExVo-MultiTask). We first applied image classification models of various sizeson mel-spectrogram representations of the vocal bursts, as is standard in soundevent detection literature. Results from these models show an increase of21.24% over the baseline system with respect to the harmonic mean of the taskmetrics, and comprise our team's main submission to the MultiTask track. Wethen sought to characterize the headroom in the MultiTask track by applying alarge pre-trained Conformer model that previously achieved state-of-the-artresults on paralinguistic tasks like speech emotion recognition and maskdetection. We additionally investigated the relationship between the sub-tasksof emotional expression, country of origin, and age prediction, and discoveredthat the best performing models are trained as single-task models, questioningwhether the problem truly benefits from a multitask setting.

Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers