SEMOUR: A Scripted Emotional Speech Repository for Urdu

TL;DR

This paper introduces SEMOUR, the first emotion-tagged Urdu speech database, enabling development of emotion recognition systems with high accuracy, supporting diverse applications like healthcare and robotics.

Contribution

The paper presents SEMOUR, a comprehensive, gender-balanced, and phonetically diverse Urdu speech emotion dataset with baseline prediction scores.

Findings

92% emotion prediction accuracy on test samples

High inter-rater agreement on emotion labels

Dataset includes 15,040 instances from eight actors

Abstract

Designing reliable Speech Emotion Recognition systems is a complex task that inevitably requires sufficient data for training purposes. Such extensive datasets are currently available in only a few languages, including English, German, and Italian. In this paper, we present SEMOUR, the first scripted database of emotion-tagged speech in the Urdu language, to design an Urdu Speech Recognition System. Our gender-balanced dataset contains 15,040 unique instances recorded by eight professional actors eliciting a syntactically complex script. The dataset is phonetically balanced, and reliably exhibits a varied set of emotions as marked by the high agreement scores among human raters in experiments. We also provide various baseline speech emotion prediction scores on the database, which could be used for various applications like personalized robot assistants, diagnosis of psychological disorders, and getting feedback from a low-tech-enabled population, etc. On a random test sample, our model correctly predicts an emotion with a state-of-the-art 92% accuracy.