Automatic Query Generation and Query Relevance Measurement for Unsupervised Language Model Adaptation of Speech Recognition
<p>Abstract</p> <p>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 th...
Main Authors: | Suzuki Motoyuki, Ito Akinori, Kajiura Yasutomo, Makino Shozo |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2009-01-01
|
Series: | EURASIP Journal on Audio, Speech, and Music Processing |
Online Access: | http://asmp.eurasipjournals.com/content/2009/140575 |
Similar Items
-
Automatic Query Generation and Query Relevance Measurement for Unsupervised Language Model Adaptation of Speech Recognition
by: Akinori Ito, et al.
Published: (2009-01-01) -
Query Recommendation Using Hybrid Query Relevance
by: Jialu Xu, et al.
Published: (2018-11-01) -
Unsupervised speech processing with applications to query-by-example spoken term detection
by: Zhang, Yaodong, Ph. D. Massachusetts Institute of Technology
Published: (2013) -
Automatic Evaluation System of English Prosody Based on Word Importance Factor
by: Motoyuki Suzuki, et al.
Published: (2008-08-01) -
Query expansion using the clustering of pseudo relevant documents with query sensitive similarity
by: Reza Khodaei, et al.
Published: (2017-01-01)