EURASIP Journal on Audio, Speech, and Music Processing

Table 19 System results of the ALBAYZIN 2018 QbE STD evaluation on COREMAH 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	0.1363	− 0.0580	0.00006	0.803	0.0000	0.0000	0.00000	1.000
B-Fusion DTW	0.2038	− 1.9448	0.00000	0.796	0.0000	0.0000	0.00000	1.000
C-PhonePost DTW	0.2075	− 1.9184	0.00000	0.792	0.0000	0.0000	0.00000	1.000
D-LVCSR	0.0037	− 0.1454	0.00000	0.996	0.0000	0.0000	0.00000	1.000
E-DTW	0.1445	0.1445	0.00003	0.827	0.0000	0.0000	0.00000	1.000
F-Combined DTW	0.0526	0.0023	0.00000	0.947	0.0000	0.0000	0.00000	1.000
G-Super-BNF DTW	0.0299	− 0.4707	0.00000	0.970	0.0000	0.0000	0.00000	1.000
H-Multilingual-BNF DTW	0.0520	− 0.8796	0.00000	0.948	0.0000	0.0000	0.00000	1.000
I-Monoph.-BNF DTW	0.0544	− 0.2688	0.00002	0.929	0.0000	0.0000	0.00000	1.000
J-Triph.-BNF DTW	0.0578	− 0.4231	0.00000	0.938	0.0000	0.0000	0.00000	1.000
K-Text STD	0.0977	− 0.5893	0.00007	0.833	0.0000	0.0000	0.00000	1.000

Back to article page