Browse › Computer Vision › Keyword Spotting › QUESST
QUESST Benchmark (Keyword Spotting)
In speech processing, keyword spotting deals with the identification of keywords in utterances.
The archive carries no text for this table; the description above is the archive's text for the task Keyword Spotting. archive 2025-07-28
Over time archive 2025-07-28
The chart needs JavaScript; the table below carries every value.
Not inferred: Cnxe, MinCnxe, ATWV, MTWV, SSF, PMUs, ISF, PMUi, PL, lowerbound . Points are placed at the row's paper date; 69 of 69 rows carry one.
Results archive 2025-07-28
Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.
| Paper | Code | Ran Syntology | Report | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | ELiRF Fusion+Length(All Queries) | 0.6023 | 0.5977 | 0.3792 | 0.3801 | – | Paper | – | 2014 | no code linked | report | ||||||
| 2 | ELiRF Fusion(All Queries) | 0.6125 | 0.6062 | 0.3896 | 0.3952 | – | Paper | – | 2014 | no code linked | report | ||||||
| 3 | CUHK(all the queries) System №2 | 0.638 | 0.585 | 0.412 | 0.413 | – | Paper | – | 2014 | no code linked | report | ||||||
| 4 | GTTS-EHU p (for the development set) | 0.6540 | 0.6353 | 0.3567 | 0.3663 | 0.064 | 0.208 | – | Paper | – | 2014 | no code linked | report | ||||
| 5 | CUHK(all the queries) System №1 | 0.682 | 0.659 | 0.412 | 0.413 | – | Paper | – | 2014 | no code linked | report | ||||||
| 6 | NNI DTW(All Queries) | 0.6925 | 0.6816 | 0.2918 | 0.2974 | – | Paper | – | 2014 | no code linked | report | ||||||
| 7 | SPL-IT(for the development set) | 0.7106 | 0.5881 | 0.4051 | 0.4052 | – | Paper | – | 2014 | no code linked | report | ||||||
| 8 | NNI Symbolic(All Queries) | 0.7322 | 0.7293 | 0.2696 | 0.2717 | – | Paper | – | 2014 | no code linked | report | ||||||
| 9 | NNI (eval) | 0.761 | 0.747 | 0.270 | 0.274 | – | Paper | – | 2015 | no code linked | report | ||||||
| 10 | NNI (dev) | 0.773 | 0.757 | 0.286 | 0.286 | – | Paper | – | 2015 | no code linked | report | ||||||
| 11 | SPL-IT-UC [All + side-info] (dev) | 0.7782 | 0.7716 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 12 | SPL-IT-UC [Hmean + side-info] (eval) | 0.7842 | 0.7786 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 13 | SPL-IT-UC [Hmean + side-info] (dev) | 0.7862 | 0.7800 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 14 | SPL-IT-UC [All + side-info] (eval) | 0.7866 | 0.7809 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 15 | SPL-IT-UC [All, no side] (dev) | 0.7873 | 0.7816 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 16 | SPL-IT-UC [Hmean, no side] (eval) | 0.7914 | 0.7856 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 17 | SPL-IT-UC [All, no side] (eval) | 0.7930 | 0.7875 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 18 | SPL-IT-UC [Hmean, no side] (dev) | 0.7957 | 0.7893 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 19 | BUT [l-fea stack DTW+slope+2w3w fusion] (eval) | 0.8447 | 0.8124 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 20 | BUT [p-fea stack DTW ] (eval) | 0.8452 | 0.8263 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 21 | BUT [l-fea stack DTW+slope] (eval) | 0.8490 | 0.8184 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 22 | BUT [p-fea stack DTW ] (dev) | 0.8580 | 0.8426 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 23 | GTM-UVigo Primary late submission (eval) | 0.871 | 0.838 | 0.592 | – | Paper | Code | 2015 | linked, not harvested | report | |||||||
| 24 | BUT [l-fea stack DTW+slope+2w3w fusion] (dev) | 0.8731 | 0.8321 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 25 | GTM-UVigo Primary late submission (dev) | 0.875 | 0.847 | 0.593 | – | Paper | Code | 2015 | linked, not harvested | report | |||||||
| 26 | BUT [l-fea stack DTW+slope] (dev) | 0.8772 | 0.8389 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 27 | BUT [l-fea stack DTW 2w+slope] (dev) | 0.8884 | 0.8569 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 28 | GTM-UVigo Contrastive late submission (dev) | 0.907 | 0.864 | 0.618 | – | Paper | Code | 2015 | linked, not harvested | report | |||||||
| 29 | NS-DTW(for the development set, all the queries) | 0.9121 | 0.8070 | 0.2261 | 0.2263 | – | Paper | – | 2014 | no code linked | report | ||||||
| 30 | GTM-UVigo Primary (dev) | 0.917 | 0.905 | 0.627 | – | Paper | Code | 2015 | linked, not harvested | report | |||||||
| 31 | BUT [l-fea stack DTW 3w+slope] (dev) | 0.9188 | 0.8801 | – | Paper | – | 2015 | no code linked | report | ||||||||
| 32 | GTM-UVigo Primary (eval) | 0.919 | 0.905 | 0.629 | – | Paper | Code | 2015 | linked, not harvested | report | |||||||
| 33 | IIT-B (dev) | 0.9213 | 0.9082 | 0.0812 | 0.816 | – | Paper | – | 2015 | no code linked | report | ||||||
| 34 | TUKE p-low late submission (for the development set) | 0.948 | 0.854 | 0.191 | 0.191 | – | Paper | – | 2014 | no code linked | report | ||||||
| 35 | IIT-B (eval) | 0.9536 | 0.9364 | 0.0254 | 0.0421 | – | Paper | – | 2015 | no code linked | report | ||||||
| 36 | TUKE p-low(for the development set) | 0.960 | 0.892 | 0.161 | 0.162 | – | Paper | – | 2014 | no code linked | report | ||||||
| 37 | TUKE p-S late submission (dev) | 0.962 | 0.940 | 0.055 | 0.059 | – | Paper | – | 2015 | no code linked | report | ||||||
| 38 | TUKE p-S late submission (eval) | 0.963 | 0.940 | 0.046 | 0.049 | – | Paper | – | 2015 | no code linked | report | ||||||
| 39 | TUKE p-S (dev) | 0.970 | 0.947 | 0.022 | 0.036 | 0.0061 | 1.874 | 2.312 | 0.250 | 0.068 | – | Paper | – | 2015 | no code linked | report | |
| 40 | TUKE g-U late submission (dev) | 0.970 | 0.951 | 0.032 | 0.035 | – | Paper | – | 2015 | no code linked | report | ||||||
| 41 | TUKE g-zero late submission(for the development set) | 0.971 | 0.922 | 0.106 | 0.107 | – | Paper | – | 2014 | no code linked | report | ||||||
| 42 | TUKE p-S (eval) | 0.971 | 0.953 | 0.002 | 0.022 | – | Paper | – | 2015 | no code linked | report | ||||||
| 43 | TUKE g-U (eval) | 0.973 | 0.953 | -0.01 | 0.023 | – | Paper | – | 2015 | no code linked | report | ||||||
| 44 | TUKE g-zero(for the development set) | 0.974 | 0.934 | 0.091 | 0.091 | – | Paper | – | 2014 | no code linked | report | ||||||
| 45 | TUKE g-U (dev) | 0.974 | 0.953 | 0.0001 | 0.031 | 0.0066 | 2.292 | 0.383 | 0.515 | 0.033 | – | Paper | – | 2015 | no code linked | report | |
| 46 | TUKE g-U late submission (eval) | 0.974 | 0.954 | 0.028 | 0.032 | – | Paper | – | 2015 | no code linked | report | ||||||
| 47 | GTM-UVigo Contrastive late submission (eval) | 0.989 | 0.852 | 0.613 | – | Paper | Code | 2015 | linked, not harvested | report | |||||||
| 48 | GTM-UVigo Contrastive (dev) | 0.998 | 0.918 | 0.635 | – | Paper | Code | 2015 | linked, not harvested | report | |||||||
| 49 | CUNY [SMO+iSAX] (dev) | 0.9988 | 0.9872 | 0.0011 | 0.0067 | – | Paper | – | 2015 | no code linked | report | ||||||
| 50 | CUNY [SMO+iSAX] (eval) | 0.9989 | 0.9870 | 0.0006 | 0.0010 | – | Paper | – | 2015 | no code linked | report | ||||||
| 51 | GTM-UVigo Contrastive (eval) | 0.999 | 0.923 | 0.633 | – | Paper | Code | 2015 | linked, not harvested | report | |||||||
| 52 | ELiRF SDTW-avg (dev) | 1.0651 | 0.8677 | 0.1446 | 0.1543 | – | Paper | – | 2015 | no code linked | report | ||||||
| 53 | CUNY [Subseq+MFCC] (dev) | 1.0658 | 0.9823 | -3.9820 | 0.0123 | – | Paper | – | 2015 | no code linked | report | ||||||
| 54 | CUNY [Subseq+MFCC] (eval) | 1.0674 | 0.9853 | -4.0205 | 0.0006 | – | Paper | – | 2015 | no code linked | report | ||||||
| 55 | ELiRF SDTW (dev) | 1.0701 | 0.8702 | 0.1404 | 0.1493 | – | Paper | – | 2015 | no code linked | report | ||||||
| 56 | ELiRF SDTW-avg (eval) | 1.0731 | 0.8751 | 0.1125 | 0.1181 | – | Paper | – | 2015 | no code linked | report | ||||||
| 57 | ELiRF SDTW (eval) | 1.1879 | 0.9338 | 0.0449 | 0.0581 | – | Paper | – | 2015 | no code linked | report | ||||||
| 58 | NTU dtw (dev) | 2.0066 | – | Paper | – | 2015 | no code linked | report | |||||||||
| 59 | NTU rnn (dev) | 2.0066 | – | Paper | – | 2015 | no code linked | report | |||||||||
| 60 | NTU dtw (eval) | 2.0067 | – | Paper | – | 2015 | no code linked | report | |||||||||
| 61 | NTU rnn (eval) | 2.0067 | – | Paper | – | 2015 | no code linked | report | |||||||||
| 62 | NNI Choi(for the development set) | 5.8940 | 0.9595 | 0.0692 | 0.0692 | – | Paper | – | 2014 | no code linked | report | ||||||
| 63 | NNI non-filtered(for the development set) | 6.0905 | 0.9571 | 0.0768 | 0.0767 | – | Paper | – | 2014 | no code linked | report | ||||||
| 64 | BUT (p-bigfusion) | 0.461 | – | Paper | – | 2014 | no code linked | report | |||||||||
| 65 | BUT (g-bigfusionnoside ) | 0.486 | – | Paper | – | 2014 | no code linked | report | |||||||||
| 66 | BUT (g-best_single) | 0.533 | – | Paper | – | 2014 | no code linked | report | |||||||||
| 67 | BUT (AKWS-cz) | 0.641 | – | Paper | – | 2014 | no code linked | report | |||||||||
| 68 | BUT (AKWS-T3-cz) | 0.673 | – | Paper | – | 2014 | no code linked | report | |||||||||
| 69 | BUT (g-LID) | 0.929 | – | Paper | – | 2014 | no code linked | report |
All 69 rows shown. 69 link to a paper page on this site; 0 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28
Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 0 rows have a graph line, from 0 distinct papers; 0 rows (0 papers) have at least one sample that ran. Counting each paper once: Syntology ran 0 of 0 samples; 0 unverified. Separately, 0 of those 0 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.
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