Investigation of the Relation between Emotional State and Acoustic Parameters in the Context of Language
Yazarlar (1)
Prof. Dr. Turgut ÖZSEVEN Tokat Gaziosmanpaşa Üniversitesi, Türkiye
| Makale Türü |
Özgün Makale
(Ulusal alan endekslerinde (TR Dizin, ULAKBİM) yayınlanan tam makale)
|
||
| Dergi Adı | European Journal of Science and Technology | ||
| Dergi ISSN | 2148-2683 | ||
| Dergi Tarandığı Indeksler | TR DİZİN | ||
| Makale Dili | İngilizce | Basım Tarihi | 12-2018 |
| Cilt / Sayı / Sayfa | 8 / 14 / 241–244 | DOI | 10.31590/ejosat.448095 |
| Makale Linki | http://dergipark.gov.tr/doi/10.31590/ejosat.448095 | ||
| UAK Araştırma Alanları |
Makine Öğrenmesi
|
||
| Özet |
| Acousticanalysis is the most basic method used for speech emotion recognition. Speechrecords are digitized by signal processing methods, and various acousticfeatures of speech are obtained by acoustic analysis methods. The relationshipbetween acoustic features and emotion has been investigated in many studies.However, studies have mostly focused on emotion recognition success or theeffects of emotions on acoustic features. The effect of spoken language onspeech emotion recognition has been investigated in a limited number. Thepurpose of this study is to investigate the variability of the relationshipbetween acoustic features and emotions according to the spoken language. Forthis purpose, three emotions (anger, fear and neutral) of three differentspoken languages (English, German and Italian) were used. In these data sets,the change in acoustic features according to spoken language was investigatedstatistically. According to the results obtained, the effect of anger on theacoustic features does not change according to the spoken language. For fear,change in spoken language shows a high similarity in Italian and German, butlow similarity in English. |
| Anahtar Kelimeler |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Google Scholar | 8 |