GOALS

 

The key objectives are:

 

·        Automated transcription of emotional and accented speech in multiple languages in the presence of spontaneous speech phenomena such as whispering and uncued language switching.

·        Enhanced text and speech processing technology such as segment boundary determination in recorded interviews, nomination of new categories and named-entity tagging during text classification  - Automated Generation of Metadata and Cataloguing

 

IBM will focus its initial efforts on processing testimonies in English.