Publication Details
Query by Example Search on Speech at Mediaeval 2015
Metze Florian (CMU)
Rodriguez-Fuentes Luis J. (EHU)
Proenca Jorge (UC)
Buzo Andi (UPB)
Lojka Martin (TUKE)
Anguera Xavier (Telefónica)
Xiong Xiao (NTU-SG)
query-by-example, query, evaluation, scoring, data, speech, search
In this paper, we describe the "Query by Example Search on Speech Task" (QUESST), held as part of the MediaEval 2015 evaluation campaign. As in previous years, the proposed task requires performing language-independent audio search in a low resource scenario. This year, the task has been designed to get as close as possible to a practical use case scenario, in which a user would like to retrieve, using speech, utterances containing a given word or short sentence, including those with limited inflectional variations of words, some filler content and/or word re-orderings. We also stressed a mismatch caused by noise and reverberations.
The paper describes track for query-by-example spoken data search. There are several types of queries, evaluation data and scoring metrics desribed.
@INPROCEEDINGS{FITPUB12268, author = "Igor Sz\H{o}ke and Florian Metze and J. Luis Rodriguez-Fuentes and Jorge Proenca and Andi Buzo and Martin Lojka and Xavier Anguera and Xiao Xiong", title = "Query by Example Search on Speech at Mediaeval 2015", pages = "1--3", booktitle = "CEUR Workshop Proceedings", journal = "CEUR Workshop Proceedings", volume = 2015, number = 1436, year = 2015, location = "Wurzen, DE", publisher = "CEUR-WS.org", ISSN = "1613-0073", language = "english", url = "https://www.fit.vut.cz/research/publication/12268" }