JST CREST Symposium on Human-Harmonized Information Technology

 

Steve Renals gave an invited talk, Natural Speech Technology, at the JST CREST Symposium on Human-Harmonized Information Technology in Kyoto on 1 April 2012.

Abstract  This talk will give an overview of the Natural Speech Technology (NST) project. NST started in 2011, and is a 5 year collaboration between the Centre for Speech Technology Research (CSTR) at the University of Edinburgh, the Speech Group at the University of Cambridge and The Speech and Hearing Research Group (SpandH), University of Sheffield. It has the aim of making speech technology perform more naturally, approaching human levels of reliability, adaptability and conversational richness. In this talk I'll give an overview of the project, including our core work on speech recognition and synthesis, and the development of applications concerning speech-driven assistive technology, media archiving, and the development of life-logging functionality.