GTM-UVigo Systems for the Query-by-Example Search on Speech Task at MediaEval 2015

TitleGTM-UVigo Systems for the Query-by-Example Search on Speech Task at MediaEval 2015
Publication TypeConference Paper
Year of Publication2015
AuthorsLópez Otero, P, Docío Fernández, L, García Mateo, C
Conference NameProceedings of the MediaEval 2015 Workshop
Date Published09/2015
AbstractIn this paper, we present the systems developed by GTM- UVigo team for the query by example search on speech task (QUESST) at MediaEval 2015. The systems consist in a fusion of 11 dynamic time warping based systems that use phoneme posteriorgrams for speech representation; the pri- mary system introduces a technique to select the most rele- vant phonetic units on each phoneme decoder, leading to an improvement of the search results.
Citation Key566