Abstract
In this paper is described a new resource for speech processing for Romanian language. Because the sentences from the recordings are expressed with seven emotions, this database can be used by an automatically emotion recognition for medical application (for example the prevention of anxiety), for intelligent human machine interfaces and other. Comparing with other emotional corpuses, this corpus Emo-IIT has only unprofessional voices, and because the recordings are not made by actors is possible to obtain lower percent in the emotion recognition. This resource will be available free on the web only for educational and research purposes. This paper is dedicated to the 150th anniversary of the Romanian Academy.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
