Back to Results
First PageMeta Content
Science / Estimation theory / Automatic identification and data capture / Computer accessibility / Speech recognition / Posterior probability / Language model / N-gram / Lattice / Statistics / Computational linguistics / Probability


LATTICE-BASED UNSUPERVISED MLLR FOR SPEAKER ADAPTATION Mukund Padmanabhan, George Saon and Geoffrey Zweig IBM T. J. Watson Research Center P. O. Box 218, Yorktown Heights, NYABSTRACT
Add to Reading List

Document Date: 2006-12-20 19:25:02

Open Document

File Size: 82,33 KB

Share Result on Facebook

City

Orlando / Istanbul / Beijing / Budapest / LATTICE / Yokohama / /

Company

IBM / Wall Street Journal / MIT Press / UNSUPERVISED MLLR / /

Country

Hungary / Japan / China / /

Facility

Harvard University / /

IndustryTerm

speech recognition systems / subsequent processing / then computing posterior word occupancy probabilities / speaker independent systems / large vocabulary telephony applications / /

Organization

Center for Research / Harvard University / MIT / /

Person

Geoffrey Zweig / Dean Null / George Saon / Dan Hi / Gene Figure / /

Position

SPEAKER / first-pass speaker / QSR TVUSW.RT / /

ProvinceOrState

Florida / New York / /

PublishedMedium

the Wall Street Journal / the Consensual Post / /

Technology

Alpha / speech recognition / pdf / /

URL

http /

SocialTag