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

The goal of our research is to automatically retrieve the satisfaction andthe frustration in real-life call-center conversations. This study focuses anindustrial application in which the customer satisfaction is continuouslytracked down to improve customer services. To compensate the lack of largeannotated emotional databases, we explore the use of pre-trained speechrepresentations as a form of transfer learning towards AlloSat corpus.Moreover, several studies have pointed out that emotion can be detected notonly in speech but also in facial trait, in biological response or in textualinformation. In the context of telephone conversations, we can break down theaudio information into acoustic and linguistic by using the speech signal andits transcription. Our experiments confirms the large gain in performanceobtained with the use of pre-trained features. Surprisingly, we found that thelinguistic content is clearly the major contributor for the prediction ofsatisfaction and best generalizes to unseen data. Our experiments conclude tothe definitive advantage of using CamemBERT representations, however thebenefit of the fusion of acoustic and linguistic modalities is not as obvious.With models learnt on individual annotations, we found that fusion approachesare more robust to the subjectivity of the annotation task. This study alsotackles the problem of performances variability and intends to estimate thisvariability from different views: weights initialization, confidence intervalsand annotation subjectivity. A deep analysis on the linguistic contentinvestigates interpretable factors able to explain the high contribution of thelinguistic modality for this task.

Acoustic and linguistic representations for speech continuous emotion recognition in call center conversations