Query-Driven Strategy for On-the-Fly Term Spotting in Spontaneous Speech. (2nd February 2010)

• Record Type: Journal Article
• Authors: Rouvier, Mickael; Linarès, Georges; Lecouteux, Benjamin
• Other Names: Wu Chung-Hsien Academic Editor.
• Is Part Of: EURASIP journal on audio, speech, and music processing. Volume 2010(2010)
• Publication Date: 2010-02-02
• Subjects: Sound -- Recording and reproducing -- Digital techniques -- Periodicals; Computer sound processing -- Periodicals; Computer sound processing; Sound -- Recording and reproducing -- Digital techniques; Periodicals; Electronic journal; Electronic journals; 620.2
• DOI: 10.1155/2010/326578
• Languages: English
• ISSNs: 1687-4714

Abstract

Abstract : 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.