Query-driven strategy for on-the-fly term spotting in spontaneous speech

Authors:
Mickael Rouvier;Georges Linarès;Benjamin Lecouteux
Affiliations:
LIA, University of Avignon, Avignon Cedex 1, France;LIA, University of Avignon, Avignon Cedex 1, France;LIA, University of Avignon, Avignon Cedex 1, France
Venue:
EURASIP Journal on Audio, Speech, and Music Processing - Special issue on scalable audio-content analysis
Year:
2010

Citing 7
Cited 0

A Segment-Based Wordspotter Using Phonetic Filler Models

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Fast implementation methods for Viterbi-based word-spotting

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Size matters: an empirical study of neural network training for large vocabulary continuous speech recognition

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Vocabulary independent spoken term detection

SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
Discriminative keyword spotting

Speech Communication
General indexation of weighted automata: application to spoken utterance retrieval

SpeechIR '04 Proceedings of the Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004
Approaches to reduce the effects of OOV queries on indexed spoken audio

IEEE Transactions on Multimedia

Quantified Score

Hi-index	0.00

Visualization

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.