ShEMO: a large-scale validated database for Persian speech emotion detection

• Published in: Language Resources and Evaluation Vol. 53; no. 1; pp. 1 - 16
• Main Authors: Nezami, Omid Mohamad, Lou, Paria Jamshid, Karami, Mansoureh
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer 01-03-2019; Springer Netherlands; Springer Nature B.V
• Subjects: Computational Linguistics; Computer Science; Corpus linguistics; Emotions; Language and Literature; Linguistics; Original Paper; Persian language; Radio; Social Sciences; Speech; Speech recognition; Support vector machines; Speech database; Benchmark; Persian; Emotional speech; Emotion detection
• ISSN: 1574-020X; 1572-8412; 1574-0218
• DOI: 10.1007/s10579-018-9427-x

This paper introduces a large-scale, validated database for Persian called Sharif Emotional Speech Database (ShEMO). The database includes 3000 seminatural utterances, equivalent to 3 h and 25 min of speech data extracted from online radio plays. The ShEMO covers speech samples of 87 native-Persian speakers for five basic emotions including anger, fear, happiness, sadness and surprise, as well as neutral state. Twelve annotators label the underlying emotional state of utterances and majority voting is used to decide on the final labels. According to the kappa measure, the inter-annotator agreement is 64% which is interpreted as "substantial agreement". We also present benchmark results based on common classification methods in speech emotion detection task. According to the experiments, support vector machine achieves the best results for both genderindependent (58.2%) and gender-dependent models (female = 59.4%, male = 57.6%). The ShEMO will be available for academic purposes free of charge to provide a baseline for further research on Persian emotional speech.