EURASIP Journal on Audio, Speech, and Music Processing

Table 17 System results of the ALBAYZIN 2018 QbE STD evaluation on MAVIR test data for single-word (Single) and multi-word (Multi) queries

From: Search on speech from spoken queries: the Multi-domain International ALBAYZIN 2018 Query-by-Example Spoken Term Detection Evaluation

	Single				Multi
System ID	MTWV	ATWV	p(FA)	p(Miss)	MTWV	ATWV	p(FA)	p(Miss)
A-Hybrid DTW+LVCSR	0.1905	0.0919	0.00017	0.637	0.7562	0.6646	0.00016	0.083
B-Fusion DTW	0.2586	0.2543	0.00007	0.673	0.7500	0.7271	0.00000	0.250
C-PhonePost DTW	0.2146	0.2052	0.00003	0.759	0.7500	0.7500	0.00000	0.250
D-LVCSR	0.1239	0.0800	0.00008	0.795	0.6437	0.6125	0.00002	0.333
E-DTW	0.1356	0.1356	0.00000	0.860	0.5000	0.4771	0.00000	0.500
F-Combined DTW	0.0945	0.0872	0.00004	0.863	0.7271	0.5896	0.00002	0.250
G-Super-BNF DTW	0.0788	0.0112	0.00008	0.839	0.7271	0.3375	0.00002	0.250
H-Multilingual-BNF DTW	0.0995	− 0.0244	0.00003	0.872	0.6437	0.3604	0.00002	0.333
I-Monoph.-BNF DTW	0.0958	0.0545	0.00002	0.882	0.7271	0.5208	0.00002	0.250
J-Triph.-BNF DTW	0.0886	0.0475	0.00004	0.873	0.7042	0.3146	0.00005	0.250
K-Text STD	0.5316	0.5139	0.00011	0.361	0.7500	0.5833	0.00000	0.250

Back to article page