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

In recent years, speech emotion recognition (SER) has been used in wideranging applications, from healthcare to the commercial sector. In addition tosignal processing approaches, methods for SER now also use deep learningtechniques. However, generalizing over languages, corpora and recordingconditions is still an open challenge in the field. Furthermore, due to theblack-box nature of deep learning algorithms, a newer challenge is the lack ofinterpretation and transparency in the models and the decision making process.This is critical when the SER systems are deployed in applications thatinfluence human lives. In this work we address this gap by providing anin-depth analysis of the decision making process of the proposed SER system.Towards that end, we present low-complexity SER based on undercomplete- anddenoising- autoencoders that achieve an average classification accuracy of over55\% for four-class emotion classification. Following this, we investigate theclustering of emotions in the latent space to understand the influence of thecorpora on the model behavior and to obtain a physical interpretation of thelatent embedding. Lastly, we explore the role of each input feature towards theperformance of the SER.

Towards Interpretable and Transferable Speech Emotion Recognition: Latent Representation Based Analysis of Features, Methods and Corpora