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

Due to the high variation in the application requirements of sound eventdetection (SED) systems, it is not sufficient to evaluate systems only in asingle operating mode. Therefore, the community recently adopted the polyphonicsound detection score (PSDS) as an evaluation metric, which is the normalizedarea under the PSD receiver operating characteristic (PSD-ROC). It summarizesthe system performance over a range of operating modes resulting from varyingthe decision threshold that is used to translate the system output scores intoa binary detection output. Hence, it provides a more complete picture of theoverall system behavior and is less biased by specific threshold tuning.However, besides the decision threshold there is also the post-processing thatcan be changed to enter another operating mode. In this paper we propose thepost-processing independent PSDS (piPSDS) as a generalization of the PSDS.Here, the post-processing independent PSD-ROC includes operating points fromvarying post-processings with varying decision thresholds. Thus, it summarizeseven more operating modes of an SED system and allows for system comparisonwithout the need of implementing a post-processing and without a bias due todifferent post-processings. While piPSDS can in principle combine differenttypes of post-processing, we hear, as a first step, present median filterindependent PSDS (miPSDS) results for this year's DCASE Challenge Task4asystems. Source code is publicly available in our sed_scores_eval package(https://github.com/fgnt/sed_scores_eval).

Post-Processing Independent Evaluation of Sound Event Detection Systems