IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Regular Section
Automatic Lecture Transcription Based on Discriminative Data Selection for Lightly Supervised Acoustic Model Training
Sheng LIYuya AKITATatsuya KAWAHARA
Author information
JOURNALS FREE ACCESS

Volume E98.D (2015) Issue 8 Pages 1545-1552

Details
Download PDF (1172K) Contact us
Abstract

The paper addresses a scheme of lightly supervised training of an acoustic model, which exploits a large amount of data with closed caption texts but not faithful transcripts. In the proposed scheme, a sequence of the closed caption text and that of the ASR hypothesis by the baseline system are aligned. Then, a set of dedicated classifiers is designed and trained to select the correct one among them or reject both. It is demonstrated that the classifiers can effectively filter the usable data for acoustic model training. The scheme realizes automatic training of the acoustic model with an increased amount of data. A significant improvement in the ASR accuracy is achieved from the baseline system and also in comparison with the conventional method of lightly supervised training based on simple matching.

Information related to the author
© 2015 The Institute of Electronics, Information and Communication Engineers
Previous article Next article

Altmetrics
Recently visited articles
Journal news & Announcements
  • Please contact trans-d [a] ieice.org, if you want to unlock PDF security.
feedback
Top