Search
Search Funnelback University
- Refined by:
- Date: 2009
1 -
10 of
15
search results for KaKaoTalk:vb20 200 |u:mi.eng.cam.ac.uk
where 0
match all words and 15
match some words.
Results that match 1 of 2 words
-
paper_pcw_v1.dvi
mi.eng.cam.ac.uk/research/projects/AGILE/publications/park_interspeech09.pdf7 Oct 2009: Frame accuracies are given foreachof the 200 hours subset MLPs in Table 1 and all subset networksgive similar results. ... 1The best performing 200 hours subsets MLPs.2The GALEeval07 non-sequestered testset version is used. -
Context Dependent Language Model Adaptation X. Liu, M. J. ...
mi.eng.cam.ac.uk/~mjfg/liu_INTER08.pdf2 Mar 2009: word - - 150.3 69.7 209.8. class. 50 166.6 76.1 217.9exchange 100 164.4 74.8 216.6algorithm 200 160.9 73.5 214.8. ... 400 159.7 73.0 213.950 165.0 73.6 213.5. weight 100 163.5 73.4 213.1merge 200 162.4 73.1 213.0. -
EM_spd_D4Tech.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/Shin_TR626.pdf4 Aug 2009: 300 200 100 0 100 200 3001. 1.05. 1.1. 1.15. 1.2. ... 9. 300 200 100 0 100 200 3001. 1.05. 1.1. 1.15. -
Learning to Track with Multiple Observers Björn StengerComputer…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2009-CVPR-hand-trackingpdf28 Jul 2009: 1. 0 100 200 300 400 5000. 0.1. 0.2. 0.3. 0.4. -
TRAINING AND ADAPTING MLP FEATURES FOR ARABIC SPEECH RECOGNITION
mi.eng.cam.ac.uk/research/projects/AGILE/publications/park_icassp09.pdf7 Oct 2009: The 260K word-list. Training data Test Acc. (%)200 hours 63.551350 hours 65.16. ... Table 1. Frame accuracies of the 200 hours and the 1350 hours MLP. -
Model-Based Approaches to Speaker andEnvironment Adaptation Mark…
mi.eng.cam.ac.uk/~mjfg/mjfg_china09.pdf28 Apr 2009: C1(nst xst ). )). 20 15 10 5 0 5 10 15 200. ... 20 15 10 5 0 5 10 15 200. 2. 4. -
paramStudy_V_(TechR).dvi
mi.eng.cam.ac.uk/reports/svr-ftp/Shin_TR600.pdf4 Aug 2009: It is changed over the. range of 200 m/s. The results in Figure 6 are similar to those for the lateral focus in Figure 2. ... 12. 200 100 0 100 2006. 3. 0. 3. 6. 9. -
report.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/ijaz_tr635.pdf20 Aug 2009: Table 2: RMSE(mm) for the in vitro experiments. A total of 200 trials were performed on 5 datasets. ... For each similarity measure, 5 simulations were performedper dataset (see Table 2) giving a total of 200 simulations over four optimisation algorithms -
Learning to Track with Multiple Observers Björn StengerComputer…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2009-CVPR-hand-trackerpdf.pdf28 Jul 2009: 1. 0 100 200 300 400 5000. 0.1. 0.2. 0.3. 0.4. -
doi:10.1016/j.patrec.2008.04.005
mi.eng.cam.ac.uk/~cipolla/archive/Publications/article/2008-PR-car-video-database.pdf28 Jul 2009: Rather than pixel intensities directly,the image features being classified are grouped as 200 texton (Leu-ng and Malik, 2001) clusters.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.