Automatic Query Generation and Query Relevance Measurement for Unsupervised Language Model Adaptation of Speech Recognition

Automatic Query Generation and Query Relevance Measurement for Unsupervised Language Model Adaptation of Speech Recognition

We are developing a method of Web-based unsupervised language model adaptation for recognition of spoken documents. The proposed method chooses keywords from the preliminary recognition result and retrieves Web documents using the chosen keywords. A problem is that the selected keywords tend to cont...

Full description

Bibliographic Details
Main Authors: Akinori Ito, Yasutomo Kajiura, Motoyuki Suzuki, Shozo Makino
Format: Article
Language:English
Published: SpringerOpen 2009-01-01
Series:EURASIP Journal on Audio, Speech, and Music Processing
Online Access:http://dx.doi.org/10.1155/2009/140575

Similar Items

Similar Items