The IIT-B Query-by-Example System for MediaEval 2015
This paper describes the system developed at I.I.T. Bombay for Query-by-Example Search on Speech Task (QUESST) within the MediaEval 2015 evaluation framework. Our system preprocesses the data to remove noise and performs subsequence DTW on posterior/bottleneck features obtained using four phone recognition systems to detect the queries. Scores from each of these subsystems are fused to get the single score per query-utterance pair which is then calibrated with respect to the cross entropy evaluation metric.
PDFTasks
Datasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Keyword Spotting | QUESST | IIT-B (dev) | Cnxe | 0.9213 | # 33 | |
MinCnxe | 0.9082 | # 44 | ||||
ATWV | 0.0812 | # 19 | ||||
MTWV | 0.816 | # 1 | ||||
Keyword Spotting | QUESST | IIT-B (eval) | Cnxe | 0.9536 | # 35 | |
MinCnxe | 0.9364 | # 51 | ||||
ATWV | 0.0254 | # 27 | ||||
MTWV | 0.0421 | # 25 |