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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Speech Emotion Recognition (SER) is the task of identifying the emotionexpressed in a spoken utterance. Emotion recognition is essential in buildingrobust conversational agents in domains such as law, healthcare, education, andcustomer support. Most of the studies published on SER use datasets created byemploying professional actors in a noise-free environment. In natural settingssuch as a customer care conversation, the audio is often noisy with speakersregularly switching between different languages as they see fit. We have workedin collaboration with a leading unicorn in the Conversational AI sector todevelop Natural Speech Emotion Dataset (NSED). NSED is a natural code-mixedspeech emotion dataset where each utterance in a conversation is annotated withemotion, sentiment, valence, arousal, and dominance (VAD) values. In thispaper, we show that by incorporating word-level VAD value we improve on thetask of SER by 2%, for negative emotions, over the baseline value for NSED.High accuracy for negative emotion recognition is essential because customersexpressing negative opinions/views need to be pacified with urgency, lestcomplaints and dissatisfaction snowball and get out of hand. Escalation ofnegative opinions speedily is crucial for business interests. Our study thencan be utilized to develop conversational agents which are more polite andempathetic in such situations.

"We care": Improving Code Mixed Speech Emotion Recognition in Customer-Care Conversations