Abstract
Emotional content analysis is getting more and more present in speech-based human machine interaction, such as emotion recognition and expressive speech synthesis. In this framework, this paper aims to compare the emotional content of a pair of speech signals, uttered by different speakers and not necessarily having the same text. This exploratory work employs machine learning methods to analyze emotional content in speech from different angles: (a) Evaluate the relevance of the used features in the analysis of emotions, (b) Calculate the similarity of the emotional content independently from speakers and text. The final goal is to provide a metric to compare emotional content in speech. Such a metric would form the basis for higher-level tasks, such as clustering utterances by emotional content, or applying kernel methods for expressive speech analysis.
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.
