ALBAYZIN Query-by-example Spoken Term Detection 2016 evaluation

EURASIP Journal on Audio, Speech, and Music Processing

Table 15 System results of the ALBAYZIN QbE STD 2016 evaluation on the MAVIR test data for the single-word (‘Single’) and the multi-word (‘Multi’) queries

System ID	Single				Multi
	MTWV	ATWV	p(FA)	p(Miss)	MTWV	ATWV	p(FA)	p(Miss)
A-GTM-UVigo-3-fea+DTW fusion	0.2467	0.2355	0.00008	0.675	0.7500	0.7500	0.00000	0.250
B-L2F-4-pllr fea+DTW fusion	0.2061	0.2001	0.00005	0.743	0.7042	0.7042	0.00005	0.250
C-L2F-4-likel fea+DTW fusion	0.2562	0.2355	0.00006	0.682	0.7500	0.5667	0.00000	0.250
D-ELiRF-UPV-Post+DTW	0.1737	0.1483	0.00002	0.806	0.6667	0.5833	0.00000	0.333
E-ELiRF-UPV-Post+DTWNorm	0.1689	0.1515	0.00003	0.802	0.6667	0.5833	0.00000	0.333
F-SPL-IT-UC-4-phnrec+DTW fusion	0.2356	0.1951	0.00008	0.680	0.8479	0.8021	0.00007	0.083
G-SPL-IT-UC-3-phnrec+DTW fusion	0.2371	0.2050	0.00005	0.709	0.8708	0.8708	0.00005	0.083
H-SPL-IT-UC-2-LIphnrec+DTW fusion	0.1907	0.1682	0.00005	0.760	0.6667	0.5750	0.00000	0.333
I-Text-based STD	0.6498	0.6385	0.00006	0.285	0.9167	0.4167	0.00000	0.083