Paper Info
Title
Approaches to reduce the effects of OOV queries on indexed spoken audio
Abstract
We present several novel approaches to the Out of Vocabulary (OOV) query problem for spoken audio: indexing based on syllable-like units called particles and query expansion according to acoustic confusability for a word index. We also examine linear and OOV-based combination of indexing schemes. We experiment on 75 h of broadcast news, comparing our techniques to a word index, a phoneme index and a phoneme index queried with phoneme sequences. Our results show that our approaches are superior to both a word index and a phoneme index for OOV words, and have comparable performance to the sequence of phonemes scheme. The particle system has worse performance than the acoustic query expansion scheme. The best system uses word queries for in-vocabulary words and a linear combination of the phoneme sequence scheme and acoustic query expansion for OOV words. Using the best possible weights for linear combination, this system improves the average precision from 0.35 for a word index to 0.40, a result only obtainable if the weights could be learnt on a development query set. The next best system used a word index for in-vocabulary words and the phoneme sequence system otherwise and had average precision of 0.39.
Year
DOI
Venue
2005
10.1109/TMM.2005.854429
IEEE Transactions on Multimedia
Keywords
DocType
Volume
audio signal processing,indexing,information retrieval systems,query processing,speech processing,vocabulary,OOV queries,acoustic query expansion,audio indexing,in-vocabulary words,indexed spoken audio,out of vocabulary query problem,particles,phoneme index,phoneme sequences,speech indexing,spoken document retrieval,syllable-like units,word indexing,Audio indexing,out-of-vocabulary words,speech indexing,spoken document retrieval
Journal
7
Issue
ISSN
Citations 
5
1520-9210
30
PageRank 
References 
Authors
1.55
17
3
Name
Order
Citations
PageRank
Logan, B.1301.55
Van Thong, J.-M.2301.55
P. J. Moreno341325.47