Papers › The IIT-B Query-by-Example System for MediaEval 2015
The IIT-B Query-by-Example System for MediaEval 2015
Hitesh Tulsiani, Preeti Rao
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.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Keyword Spotting | QUESST | IIT-B (dev) | ATWV | 0.0812 | #33 of 69 | Archive leaderboard | report |
| Keyword Spotting | QUESST | IIT-B (dev) | Cnxe | 0.9213 | #33 of 69 | Archive leaderboard | report |
| Keyword Spotting | QUESST | IIT-B (dev) | MTWV | 0.816 | #33 of 69 | Archive leaderboard | report |
| Keyword Spotting | QUESST | IIT-B (dev) | MinCnxe | 0.9082 | #33 of 69 | Archive leaderboard | report |
| Keyword Spotting | QUESST | IIT-B (eval) | ATWV | 0.0254 | #35 of 69 | Archive leaderboard | report |
| Keyword Spotting | QUESST | IIT-B (eval) | Cnxe | 0.9536 | #35 of 69 | Archive leaderboard | report |
| Keyword Spotting | QUESST | IIT-B (eval) | MTWV | 0.0421 | #35 of 69 | Archive leaderboard | report |
| Keyword Spotting | QUESST | IIT-B (eval) | MinCnxe | 0.9364 | #35 of 69 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections