Mining a Year of Speech

Abstract

This project focuses on large scale data analysis of audio -- specifically the spoken word.  This project will create tools to enable rapid and flexible access to over 9,000 hours of spoken audio files, containing a wide variety of speech, drawn from some of the leading British and American spoken word corpora, allowing for new kinds of linguistic analysis.

Principal Investigators

Mark Liberman, University of Pennsylvania, US, NSF
John Coleman, University of Oxford, UK, JISC
Additional Key Participants: The British Library