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

Emotion recognition in conversations is essential for ensuring advancedhuman-machine interactions. However, creating robust and accurate emotionrecognition systems in real life is challenging, mainly due to the scarcity ofemotion datasets collected in the wild and the inability to take into accountthe dialogue context. The CEMO dataset, composed of conversations betweenagents and patients during emergency calls to a French call center, fills thisgap. The nature of these interactions highlights the role of the emotional flowof the conversation in predicting patient emotions, as context can often make adifference in understanding actual feelings. This paper presents a multi-scaleconversational context learning approach for speech emotion recognition, whichtakes advantage of this hypothesis. We investigated this approach on bothspeech transcriptions and acoustic segments. Experimentally, our method usesthe previous or next information of the targeted segment. In the text domain,we tested the context window using a wide range of tokens (from 10 to 100) andat the speech turns level, considering inputs from both the same and opposingspeakers. According to our tests, the context derived from previous tokens hasa more significant influence on accurate prediction than the following tokens.Furthermore, taking the last speech turn of the same speaker in theconversation seems useful. In the acoustic domain, we conducted an in-depthanalysis of the impact of the surrounding emotions on the prediction. Whilemulti-scale conversational context learning using Transformers can enhanceperformance in the textual modality for emergency call recordings,incorporating acoustic context is more challenging.

Multiscale Contextual Learning for Speech Emotion Recognition in Emergency Call Center Conversations