DEMoS: an Italian emotional speech corpus: Elicitation methods, machine learning, and perception.
We present DEMoS (Database of Elicited Mood in Speech), a new, large database with Italian emotional speech: 68 speakers, some 9 k speech samples. As Italian is under-represented in speech emotion research, for a comparison with the state-of-the-art, we model the 'big 6 emotions' and guilt. Besides...
| Publicado en: | Language Resources & Evaluation Vol. 54; no. 2; pp. 341 - 384 |
|---|---|
| Autores principales: | , , , , |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Jun2020
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=143152353&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 143152353 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: Jun2020 vid: 54 iid: 2 pid: 237 pub: Springer Nature artinfo: ui: 143152353 10.1007/s10579-019-09450-y ppf: 341 ppct: 43 formats: fmt: – @attributes: type: T – @attributes: type: P size: 1.7MB tig: atl: DEMoS: an Italian emotional speech corpus: Elicitation methods, machine learning, and perception. aug: au: Parada-Cabaleiro, Emilia Costantini, Giovanni Batliner, Anton Schmitt, Maximilian Schuller, Björn W. affil: ZD.B Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy su: Machine learning Perception testing Support vector machines Speech Sensory perception sug: subj: Machine learning Perception testing Support vector machines Speech Sensory perception keyword: Elicitation Emotional speech Italian corpus Mood induction procedures Prototype ab: We present DEMoS (Database of Elicited Mood in Speech), a new, large database with Italian emotional speech: 68 speakers, some 9 k speech samples. As Italian is under-represented in speech emotion research, for a comparison with the state-of-the-art, we model the 'big 6 emotions' and guilt. Besides making available this database for research, our contribution is three-fold: First, we employ a variety of mood induction procedures, whose combinations are especially tailored for specific emotions. Second, we use combinations of selection procedures such as an alexithymia test and self- and external assessment, obtaining 1,5 k (proto-) typical samples; these were used in a perception test (86 native Italian subjects, categorical identification and dimensional rating). Third, machine learning techniques—based on standardised brute-forced openSMILE ComParE features and support vector machine classifiers—were applied to assess how emotional typicality and sample size might impact machine learning efficiency. Our results are three-fold as well: First, we show that appropriate induction techniques ensure the collection of valid samples, whereas the type of self-assessment employed turned out not to be a meaningful measurement. Second, emotional typicality—which shows up in an acoustic analysis of prosodic main features—in contrast to sample size is not an essential feature for successfully training machine learning models. Third, the perceptual findings demonstrate that the confusion patterns mostly relate to cultural rules and to ambiguous emotions. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Language Resources & Evaluation is a copyright of Springer, 2020. All Rights Reserved. item: Language Resources & Evaluation holder: Springer Nature dt: @attributes: year: 2020 holdings: @attributes: islocal: N |
|---|