"INFO" - INFORMATION TECHNOLOGY
		INFO BIO NANO MACRO ENVIRO Information Technology at MIT Artificial Intelligence Laboratory Center for Biological and Computational Learning Center for Transportation and Logistics d'Arbeloff Laboratory for Information Systems and Technology Laboratory for Computer Science Laboratory for Information and Decision Systems Media Lab Project Oxygen (LCS) Research Laboratory for Electronics			A NEW APPROACH TO SPEECH RECOGNITION Thomas Knight Department of Electrical Engineering and Computer Science Speech is our most natural communication medium, but difficulties with present-day speech-recognition algorithms prevent its widespread use in our interaction with machines. Current algorithms have extreme difficulty in noisy environments and with new speakers. Speech recognizers have high error rates - even the best in ideal conditions misunderstand 1 in 20 words, with recognition dropping to 50% in noisy environments. They also have difficulty with previously unheard speakers and dialects. These failures, which suggest that we don't really yet understand what differentiates particular sounds in the language, have limited the usefulness of current speech recognition technology. This project will develop a novel, non-linear representation for speech that addresses the shortcomings of existing representations. It will greatly improve the ability of machines to understand human speech and thus make communicating with machines as easy as talking on the phone.
						MIT School of Engineering © Copyright 2002-2005 Massachusetts Institute of Technology Deshpande Center for Technological Innovation Massachusetts Institute of Technology 77 Massachusetts Avenue, Room 1-229 Cambridge, MA 02139 617-253-0943 617-253-8459 fax