DC Field | Value | Language |
---|---|---|
dc.contributor.author | 이수장 | ko |
dc.contributor.author | 박경미 | ko |
dc.contributor.author | 오영환 | ko |
dc.date.accessioned | 2010-04-13T07:09:01Z | - |
dc.date.available | 2010-04-13T07:09:01Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2008-09 | - |
dc.identifier.citation | 말소리, v.1, no.67, pp.149 - 166 | - |
dc.identifier.issn | 1226-1173 | - |
dc.identifier.uri | http://hdl.handle.net/10203/17647 | - |
dc.description.abstract | In spoken document retrievals (SDR), subword (typically phonemes) indexing term is used to avoid the out-of-vocabulary (OOV) problem. It makes the indexing and retrieval process independent from any vocabulary. It also requires a small corpus to train the acoustic model. However, subword indexing term approach has a major drawback. It shows higher word error rates than the large vocabulary continuous speech recognition (LVCSR) system. In this paper, we propose an probabilistic slot detection and n-gram based string matching method for phone based spoken document retrievals to overcome high error rates of phone recognizer. Experimental results have shown 9.25% relative improvement in the mean average precision (mAP) with 1.7 times speed up in comparison with the baseline system. | - |
dc.language | Korean | - |
dc.language.iso | ko | en |
dc.publisher | 대한음성학회 | - |
dc.title | 음소인식 오류에 강인한 N-gram 기반 음성 문서 검색 | - |
dc.title.alternative | N-gram Based Robust Spoken Document Retrievals for Phoneme Recognition Errors | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.citation.volume | 1 | - |
dc.citation.issue | 67 | - |
dc.citation.beginningpage | 149 | - |
dc.citation.endingpage | 166 | - |
dc.citation.publicationname | 말소리 | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.identifier.kciid | ART001279135 | - |
dc.contributor.localauthor | 오영환 | - |
dc.contributor.nonIdAuthor | 이수장 | - |
dc.contributor.nonIdAuthor | 박경미 | - |
dc.subject.keywordAuthor | Probabilistic slot detection | - |
dc.subject.keywordAuthor | N-gram matching | - |
dc.subject.keywordAuthor | Spoken document retrieval. | - |
dc.subject.keywordAuthor | Probabilistic slot detection | - |
dc.subject.keywordAuthor | N-gram matching | - |
dc.subject.keywordAuthor | Spoken document retrieval. | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.