From Tale to Speech: Ontology-based Emotion and Dialogue Annotation of Fairy Tales with a TTS Output

Christian Eisenreich, Jana Ott, Tonio Süßdorf, Christian Willms, Thierry Declerck

In: Proceedings of ISWC 2014. International Semantic Web Conference (ISWC-14) 13th October 19-23 Riva del Garda Italy Springer 10/2014.


In this demo and poster paper, we describe the concept and implementation of an ontology-based storyteller for fairy tales. Its main functions are (i) annotating the tales by extracting timeline information, characters and dialogues with corresponding emotions expressed in the utterances, (ii) populating an existing ontology for fairy tales with the previously extracted information and (iii) using this ontology to generate a spoken version of the tales. Common natural language processing technologies and resources, such as part-of-speech tagging, chunking and semantic networks have been successfully used for the implementation of the three tasks mentioned just above, including the integration of an opensource text-to-speech system. The code of the system is publicly available.


paper_120_ISWC14.pdf (pdf, 191 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence