SEarching Swiss Audio MEmories
Audio archives of cultural heritage represent an important form of saving people's collective memories. Those initiatives have flourished in several countries and aim at preserving the local spoken audio heritage. The size of those collections is constantly increasing and demands considerable efforts in annotation and categorization. Automatically structuring and indexing spoken audio archives is an active research field with focus on well defined types of data like Broadcast recordings, voice-mail, lectures or meetings. However spoken data from the cultural heritage presents considerably more heterogeneous contents respect to conventional Broadcast recordings.
Beside presentations, interviews, testimonies, debates, they also contains folkloric literary productions, i.e., recitals, poems and theatrical representations which represent an important part of those archives as well as a fundamental element of the local cultural heritage. Those data have significantly different structure and stylistic features compared to conventional broadcast data and spoken language technologies appear of limited applications on those archives.
Furthermore cultural heritage archives, spanning several decades of recordings, present considerable variabilities in terms of audio quality further increasing the need of robust audio processing.
SESAME aims at advancing the state-of-the-art in speech processing and spoken language understanding for automatically structuring data from the spoken cultural heritage archives. Technical challenges include speaker segmentation and clustering, role recognition as well as topic/story segmentation and tracking on very heterogeneous data.
Partners
Idiap Research Institute
