ELiRF at MediaEval 2015: Query by Example Search on Speech Task (QUESST)
n this paper, we present the systems that the Natural Language Engineering and Pattern Recognition group (ELiRF) has submitted to the MediaEval 2015 Query by Example Search on Speech Task. All of them are based on a Subsequence Dynamic Time Warping algorithm. The systems use information from outside the task (low-resources systems).
PDF
Datasets
Add Datasets
introduced or used in this paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Keyword Spotting | QUESST | ELiRF SDTW-avg (dev) | Cnxe | 1.0651 | # 52 | |
| MinCnxe | 0.8677 | # 37 | ||||
| ATWV | 0.1446 | # 14 | ||||
| MTWV | 0.1543 | # 15 | ||||
| Keyword Spotting | QUESST | ELiRF SDTW (eval) | Cnxe | 1.1879 | # 57 | |
| MinCnxe | 0.9338 | # 49 | ||||
| ATWV | 0.0449 | # 24 | ||||
| MTWV | 0.0581 | # 23 | ||||
| Keyword Spotting | QUESST | ELiRF SDTW-avg (eval) | Cnxe | 1.0731 | # 56 | |
| MinCnxe | 0.8751 | # 39 | ||||
| ATWV | 0.1125 | # 16 | ||||
| MTWV | 0.1181 | # 17 | ||||
| Keyword Spotting | QUESST | ELiRF SDTW (dev) | Cnxe | 1.0701 | # 55 | |
| MinCnxe | 0.8702 | # 38 | ||||
| ATWV | 0.1404 | # 15 | ||||
| MTWV | 0.1493 | # 16 |
Methods
No methods listed for this paper. Add
relevant methods here
