Automatic detection of nominal entities in speech for enriched content search
Document Type
Conference Proceeding
Publication Date
12-13-2013
Abstract
In this work, a methodology is developed to detect sentient actors in spoken stories. Meta-tags are then saved to XML files associated with the audio files. A recursive approach is used to find actor candidates and features which are then classified using machine learning approaches. Results of the study indicate that the methodology performed well on a narrative based corpus of children's stories. Using Support Vector Machines for classification, an F-measure accuracy score of 86% was achieved for both named and unnamed entities. Additionally, feature analysis indicated that speech features were very useful when detecting unnamed actors.
Publication Source (Journal or Book title)
FLAIRS 2013 - Proceedings of the 26th International Florida Artificial Intelligence Research Society Conference
First Page
190
Last Page
195
Recommended Citation
Calix, R., Javadpour, L., Khazaeli, M., & Knapp, G. (2013). Automatic detection of nominal entities in speech for enriched content search. FLAIRS 2013 - Proceedings of the 26th International Florida Artificial Intelligence Research Society Conference, 190-195. Retrieved from https://repository.lsu.edu/mechanical_engineering_pubs/1475