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

EURASIP Journal on Audio, Speech, and Music Processing

Table 13 System results of the ALBAYZIN 2018 QbE STD evaluation on COREMAH test data

System ID	MTWV	ATWV	p(FA)	p(Miss)
A-Hybrid DTW+LVCSR	0.1354	− 0.0689	0.00006	0.804
B-Fusion DTW	0.2022	− 1.9221	0.00000	0.798
C-PhonePost DTW	0.2059	− 1.9062	0.00000	0.794
D-LVCSR	0.0037	− 0.1559	0.00000	0.996
E-DTW	0.1436	0.1436	0.00003	0.828
F-Combined DTW	0.0521	0.0023	0.00000	0.948
G-Super-BNF DTW	0.0295	− 0.4763	0.00000	0.970
H-Multilingual-BNF DTW	0.0514	− 0.8895	0.00000	0.949
I-Monoph.-BNF DTW	0.0538	− 0.2779	0.00002	0.930
J-Triph.-BNF DTW	0.0572	− 0.4379	0.00000	0.939
K-Text STD	0.0966	− 0.5828	0.00007	0.835