A Fertility Channel Model for Post-Correction of Continuous Speech Recognition

View Description

Download

small (250x250 max)

medium (500x500 max)

large ( > 500x500)

Full Resolution

PDF
Text

Description

Rating
Permanent URL	http://hdl.lib.byu.edu/1877/2590
Title	A Fertility Channel Model for Post-Correction of Continuous Speech Recognition
BYU Creator	Ringger, Eric K.
Creator	Allen, James F.
Keywords	speech recognizer; word accuracy; channel model; post-correction
Description/Abstract	We have implemented a post-processor called SPEECHPP to correct word-level errors committed by an arbitrary speech recognizer. Applying a noisy-channel model, SPEECHPP uses a Viterbi beam-search that employs language and channel models. Previous work demonstrated that a simple word-for-word channel model was sufficient to yield substantial incieases in word accuracy. This paper demonstrates that some improvements in word accuracy result from augmenting the channel model with an account of word fertility in the channel. This work further demonstrates that a modern continuous speech recognizer can be used in "black-box" fashion for robustly recognizing speech for which the recognizer was not originally trained. This work also demonstrates that in the case when the recognizer can be tuned to the new task, environment, or speaker, the post-processor can also contribute to performance improvements.
Source	Eric K. Ringger and James F. Allen. October 1996. "A Fertility Channel Model for Post-Correction of Continuous Speech Recognition." Proceedings of the Fourth International Conference on Spoken Language Processing (ICSLP'96). Philadelphia, PA.;
Publisher	IEEE
Date Original	1996-10
Date Digital	2010-10-21
Language	English eng en
Publication Type	Conference Proceedings Peer-Reviewed Articles
Type	Text
Format	application/pdf
Owning Institution	Brigham Young University
BYU College	College of Physical and Mathematical Sciences
BYU Department	Computer Science
Copyright Status	(c) 1996 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.;
Copyright Use Information	http://www.lib.byu.edu/generic_copyright.html

Comments

Post a Comment for A Fertility Channel Model for Post-Correction of Continuous Speech Recognition

you wish to report:

Your comment:

Your Name:

Submit

Cancel

...

Find results with:

Searching collections:

Home A Fertility Channel Model for Post-Correction of Continuous Speech Recognition

A Fertility Channel Model for Post-Correction of Continuous Speech Recognition

Description

Tags

Comments