Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous Speech

<p/> <p>Spoken utterance retrieval was largely studied in the last decades, with the purpose of indexing large audio databases or of detecting keywords in continuous speech streams. While the indexing of closed corpora can be performed via a batch process, on-line spotting systems have t...

Full description

Bibliographic Details
Main Authors: Rouvier Mickael, Linar&#232;s Georges, Lecouteux Benjamin
Format: Article
Language:English
Published: SpringerOpen 2010-01-01
Series:EURASIP Journal on Audio, Speech, and Music Processing
Online Access:http://asmp.eurasipjournals.com/content/2010/326578
id doaj-6f6e1de44440413785db8edf2d500143
record_format Article
spelling doaj-6f6e1de44440413785db8edf2d5001432020-11-25T01:12:43ZengSpringerOpenEURASIP Journal on Audio, Speech, and Music Processing1687-47141687-47222010-01-0120101326578Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous SpeechRouvier MickaelLinar&#232;s GeorgesLecouteux Benjamin<p/> <p>Spoken utterance retrieval was largely studied in the last decades, with the purpose of indexing large audio databases or of detecting keywords in continuous speech streams. While the indexing of closed corpora can be performed via a batch process, on-line spotting systems have to synchronously detect the targeted spoken utterances. We propose a two-level architecture for on-the-fly term spotting. The first level performs a fast detection of the speech segments that probably contain the targeted utterance. The second level refines the detection on the selected segments, by using a speech recognizer based on a query-driven decoding algorithm. Experiments are conducted on both broadcast and spontaneous speech corpora. We investigate the impact of the spontaneity level on system performance. Results show that our method remains effective even if the recognition rates are significantly degraded by disfluencies.</p> http://asmp.eurasipjournals.com/content/2010/326578
collection DOAJ
language English
format Article
sources DOAJ
author Rouvier Mickael
Linar&#232;s Georges
Lecouteux Benjamin
spellingShingle Rouvier Mickael
Linar&#232;s Georges
Lecouteux Benjamin
Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous Speech
EURASIP Journal on Audio, Speech, and Music Processing
author_facet Rouvier Mickael
Linar&#232;s Georges
Lecouteux Benjamin
author_sort Rouvier Mickael
title Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous Speech
title_short Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous Speech
title_full Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous Speech
title_fullStr Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous Speech
title_full_unstemmed Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous Speech
title_sort query-driven strategy for on-the-fly term spotting in spontaneous speech
publisher SpringerOpen
series EURASIP Journal on Audio, Speech, and Music Processing
issn 1687-4714
1687-4722
publishDate 2010-01-01
description <p/> <p>Spoken utterance retrieval was largely studied in the last decades, with the purpose of indexing large audio databases or of detecting keywords in continuous speech streams. While the indexing of closed corpora can be performed via a batch process, on-line spotting systems have to synchronously detect the targeted spoken utterances. We propose a two-level architecture for on-the-fly term spotting. The first level performs a fast detection of the speech segments that probably contain the targeted utterance. The second level refines the detection on the selected segments, by using a speech recognizer based on a query-driven decoding algorithm. Experiments are conducted on both broadcast and spontaneous speech corpora. We investigate the impact of the spontaneity level on system performance. Results show that our method remains effective even if the recognition rates are significantly degraded by disfluencies.</p>
url http://asmp.eurasipjournals.com/content/2010/326578
work_keys_str_mv AT rouviermickael querydrivenstrategyforontheflytermspottinginspontaneousspeech
AT linar232sgeorges querydrivenstrategyforontheflytermspottinginspontaneousspeech
AT lecouteuxbenjamin querydrivenstrategyforontheflytermspottinginspontaneousspeech
_version_ 1725165431224795136