By Topic

Topic dependent class based language model evaluation on automatic speech recognition

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
$33 $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)
Welly Naptali ; Department of Computer Science and Engineering, Toyohashi University of Technology, Japan ; Masatoshi Tsuchiya ; Seiichi Nakagawa

A topic dependent class (TDC) language model (LM) is a topic-based LM that uses a semantic extraction method to reveal latent topic information from noun-document relation. Then a clustering for a given context is performed to define topics. Finally, a fixed window of word history is observed to decide the topic of the current event through voting in online manner. Previously, we have shown that TDC overperforms several state-of-the-art baselines in terms of perplexity. In this paper we evaluate TDC on automatic speech recognition experiment (ASR) for rescoring task. Experiments on read speech Wall Street Journal (English ASR system) and Mainichi Shimbun (Japanese ASR system) show that TDC LM improves both perplexity and word-error-rate (WER). The result shows that the proposed model gives improvements 3.0% relative on perplexity and 15.2% relative on WER for English ASR system, and 16.4% relative on perplexity and 24.3% relative on WER for Japanese ASR system.

Published in:

Spoken Language Technology Workshop (SLT), 2010 IEEE

Date of Conference:

12-15 Dec. 2010