Get 20M+ Full-Text Papers For Less Than $1.50/day. Subscribe now for You or Your Team.

Learn More →

Speech retrieval from unsegmented finnish audio using statistical morpheme-like units for segmentation, recognition, and retrieval

Speech retrieval from unsegmented finnish audio using statistical morpheme-like units for... Speech Retrieval from Unsegmented Finnish Audio Using Statistical Morpheme-Like Units for Segmentation, Recognition, and Retrieval VILLE T. TURUNEN and MIKKO KURIMO, Aalto University School of Science This article examines the use of statistically discovered morpheme-like units for Spoken Document Retrieval (SDR). The morpheme-like units (morphs) are used both for language modeling in speech recognition and as index terms. Traditional word-based methods suffer from out-of-vocabulary words. If a word is not in the recognizer vocabulary, any occurrence of the word in speech will be missing from the transcripts. The problem is especially severe for languages with a high number of distinct word forms such as Finnish. With the morph language model, even previously unseen words can be recognized by identifying its component morphs. Similarly in information retrieval queries, complex word forms, even unseen ones, can be matched to data after segmenting them to morphs. Retrieval performance can be further improved by expanding the transcripts with alternative recognition results from confusion networks. In this article, a novel retrieval evaluation corpus consisting of unsegmented Finnish radio programs, 25 queries and corresponding human relevance assessments was constructed. Previous results on using morphs and confusion networks for Finnish SDR are con rmed and http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Speech and Language Processing (TSLP) Association for Computing Machinery

Speech retrieval from unsegmented finnish audio using statistical morpheme-like units for segmentation, recognition, and retrieval

Loading next page...
 
/lp/association-for-computing-machinery/speech-retrieval-from-unsegmented-finnish-audio-using-statistical-w1Iob6FdAn

References (64)

Publisher
Association for Computing Machinery
Copyright
Copyright © 2011 by ACM Inc.
ISSN
1550-4875
DOI
10.1145/2036916.2036917
Publisher site
See Article on Publisher Site

Abstract

Speech Retrieval from Unsegmented Finnish Audio Using Statistical Morpheme-Like Units for Segmentation, Recognition, and Retrieval VILLE T. TURUNEN and MIKKO KURIMO, Aalto University School of Science This article examines the use of statistically discovered morpheme-like units for Spoken Document Retrieval (SDR). The morpheme-like units (morphs) are used both for language modeling in speech recognition and as index terms. Traditional word-based methods suffer from out-of-vocabulary words. If a word is not in the recognizer vocabulary, any occurrence of the word in speech will be missing from the transcripts. The problem is especially severe for languages with a high number of distinct word forms such as Finnish. With the morph language model, even previously unseen words can be recognized by identifying its component morphs. Similarly in information retrieval queries, complex word forms, even unseen ones, can be matched to data after segmenting them to morphs. Retrieval performance can be further improved by expanding the transcripts with alternative recognition results from confusion networks. In this article, a novel retrieval evaluation corpus consisting of unsegmented Finnish radio programs, 25 queries and corresponding human relevance assessments was constructed. Previous results on using morphs and confusion networks for Finnish SDR are con rmed and

Journal

ACM Transactions on Speech and Language Processing (TSLP)Association for Computing Machinery

Published: Oct 1, 2011

There are no references for this article.