Scheduled System Maintenance:
On Monday, April 27th, IEEE Xplore will undergo scheduled maintenance from 1:00 PM - 3:00 PM ET (17:00 - 19:00 UTC). No interruption in service is anticipated.
By Topic

Adaptive language modeling with varied sources to cover new vocabulary items

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Schwarm, S.E. ; Dept. of Comput. Sci. & Eng., Univ. of Washington, Seattle, WA, USA ; Bulyko, Ivan ; Ostendorf, M.

N-gram language modeling typically requires large quantities of in-domain training data, i.e., data that matches the task in both topic and style. For conversational speech applications, particularly meeting transcription, obtaining large volumes of speech transcripts is often unrealistic; topics change frequently and collecting conversational-style training data is time-consuming and expensive. In particular, new topics introduce new vocabulary items which are not included in existing models. In this work, we use a variety of data sources (reflecting different sizes and styles), combined using mixture n-gram models. We study the impact of the different sources on vocabulary expansion and recognition accuracy, and investigate possible indicators of the usefulness of a data source. For the task of recognizing meeting speech, we obtain a 9% relative reduction in the overall word error rate and a 61% relative reduction in the word error rate for "new" words added to the vocabulary over a baseline language model trained from general conversational speech data.

Published in:

Speech and Audio Processing, IEEE Transactions on  (Volume:12 ,  Issue: 3 )