The L2F Spoken Web Search System for Mediaeval 2013.
Alberto Abad, Ramón Fernández Astudillo, Isabel Trancoso · 2012
The INESC-ID’s Spoken Language Systems Laboratory (L 2 F) primary system developed for the Spoken Web Search task of the Mediaeval 2013 evaluation campaign consists of the fusion of six individual sub-systems exploiting 3 different language-dependent phonetic classifiers. For each phonetic classifier, an acoustic keyword spotting (AKWS) sub-system based on connectionist speech recognition and a dynamic time warping (DTW) based sub-system have been developed. The diversity in terms of phonetic classifiers and methods, together with the efficient fusion and calibration approach applied for heterogeneous sub-systems, are the key elements of the L 2 F submission. Besides the primary submission, two additional systems based on the fusion of only the AKWS and the DTW sub-systems have been developed for comparison purposes. A final multi-site system formed by the fusion of the L2F and the GTTS primary submissions has been also submitted to explore the potential of the fusion approach for very heterogeneous systems. 1.