DMCA
SpeechFind: Advances in spoken document retrieval for a national gallery of the spoken word (2005)
| Venue: | IEEE Trans. Audio, Speech, and Language Processing |
| Citations: | 22 - 5 self |
BibTeX
@ARTICLE{Hansen05speechfind:advances,
author = {John H. L. Hansen and Senior Member and Rongqing Huang and Student Member and Bowen Zhou and Michael Seadle and J. R. Deller and Aparna R. Gurijala and Mikko Kurimo and Pongtep Angkititrakul},
title = {SpeechFind: Advances in spoken document retrieval for a national gallery of the spoken word},
journal = {IEEE Trans. Audio, Speech, and Language Processing},
year = {2005},
pages = {712--730}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract—Advances in formulating spoken document retrieval for a new National Gallery of the Spoken Word (NGSW) are addressed. NGSW is the first large-scale repository of its kind, consisting of speeches, news broadcasts, and recordings from the 20th century. After presenting an overview of the audio stream content of the NGSW, with sample audio files from U.S. Presidents from 1893 to the present, an overall system diagram is proposed with a discussion of critical tasks associated with effective audio in-formation retrieval. These include advanced audio segmentation, speech recognition model adaptation for acoustic background noise and speaker variability, and information retrieval using natural language processing for text query requests that include document and query expansion. For segmentation, a new eval-uation criterion entitled fused error score (FES) is proposed, followed by application of the CompSeg segmentation scheme on
Keyphrases
spoken word spoken document retrieval national gallery overall system diagram effective audio in-formation retrieval information retrieval compseg segmentation scheme abstract advance text query request critical task u.s. president speech recognition model adaptation natural language processing fused error score advanced audio segmentation new national gallery audio stream content query expansion news broadcast sample audio file acoustic background noise 20th century new eval-uation criterion first large-scale repository speaker variability
