The L2F Spoken Web Search System for Mediaeval 2013

The INESC-ID’s Spoken Language Systems Laboratory (LF) 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 LF 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.