BUT QUESST 2014 System Description
The primary system we submitted was composed of 11 subsystems as the required run. 3 subsystems are based on Acoustic Keyword Spotting (AKWS) and 8 on Dynamic Time Warping (DTW). The AKWS systems were based only on phoneme posteriors while the DTW subsystems were based on both phoneme posteriors and Bottle-Neck features (BN) as input. The underlying phoneme posterior estimators / bottle-neck feature extractors were both in-language (Czech) and out-of-language (other 4 languages). We also performed experiments on T1/T2/T3 types of query, system calibration and fusion based on binary logistic regression
PDF
Datasets
Add Datasets
introduced or used in this paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Keyword Spotting | QUESST | BUT (p-bigfusion) | MinCnxe | 0.461 | # 1 | |
| Keyword Spotting | QUESST | BUT (g-bigfusionnoside ) | MinCnxe | 0.486 | # 2 | |
| Keyword Spotting | QUESST | BUT (g-best_single) | MinCnxe | 0.533 | # 3 | |
| Keyword Spotting | QUESST | BUT (AKWS-cz) | MinCnxe | 0.641 | # 9 | |
| Keyword Spotting | QUESST | BUT (AKWS-T3-cz) | MinCnxe | 0.673 | # 11 | |
| Keyword Spotting | QUESST | BUT (g-LID) | MinCnxe | 0.929 | # 48 |
Methods
No methods listed for this paper. Add
relevant methods here
