Search
Search Funnelback University
- Refined by:
- Date: 2004
1 -
20 of
24
search results for katalk:za31 24 / / / / / |u:mi.eng.cam.ac.uk
where 0
match all words and 24
match some words.
Results that match 1 of 2 words
-
Diarisation Research at CUED Sue Tranter and Srinivasan Umesh ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/tranter_mdetechmay04.pdf29 Apr 2004: 29.44 0 6standard-BIC-judge, full cov 24.62 2 2standard-BIC-judge, diag cov 23.90 3 1standard-BIC-judge, 128mix GMM 23.76 5 1IDIAP-BIC-judge, full ... 37.92 10.74 24.62BIC-judge, diag cov 30.30 19.94 18.11 31.05 37.92 10.74 23.90BIC-judge, 128mix GMM -
Speaker Diarisation for Broadcast News
mi.eng.cam.ac.uk/reports/full_html/tranter_odyssey04.html/14 Jun 2004: 9.1. 25.54. 29.7. 46.14. CU. MIT. 2.1. 2.5. 5.3. 24.23. 24.7. ... Adv. Seg. Clust. Score. Metric. NONE. CUED. MIT. 24.23. Primary. CUED_TDT4. -
SVMs, Generative Kernels & Maximum MarginStatistical Models Mark…
mi.eng.cam.ac.uk/~mjfg/ISM_talk.pdf9 Dec 2004: Cambridge UniversityEngineering Department. Institute of Statistical Mathematics 24. SVMs, Generative Kernels and Maximum Margin Statistical Models. -
Experiments with Fisher Data Gunnar Evermann, Bin Jia, Kai ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/evermann_sttmay04.pdf25 May 2004: System MPE Prior eval03 Male Female. MPE-GI Dynamic MMI 25.9 27.3 24.5MPE-GD MPE-GI model 25.6 27.1 24.1. ... Gaussianised 29.8 21.9 26.0CN 28.7 21.3 25.1. CNC 28.1 20.8 24.6. • -
DEVELOPMENT OF THE 2003 CU-HTK CONVERSATIONAL TELEPHONE…
mi.eng.cam.ac.uk/reports/svr-ftp/evermann_icassp2004.pdf27 May 2004: purpose WER. P1 supervision for VTLN 34.2P2 supervision for MLLR 28.4P3 lattice generation 24.8. ... System (P4) A B C DSAT HLDA SPron non-HLDA23.0 23.6 23.4 24.8. -
Metadata at CUED: Progress, Plans, and Issues Marcus Tomalin, ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/tomalin_earsfeb04.pdf22 Mar 2004: BIC-global (2-way) 6.25 6.25 26.13 25.21BIC-local (2-way) 7.25 - 25.54 25.12BIC-local (2-way) - 6.75 26.47 24.27. • ... Approx. 8% absolute (24% relative) reduction in DER. • Stability also greatly increased: standard deviation when using many input -
paper.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/liu_icassp2004.pdf29 May 2004: Gauss 24.0 20.7 20.7 17.7 16.0WER (%) 35.3 35.1 35.2 35.3 35.5. ... The 16 component systems was then iteratively split until thenumber of components was 24. -
Cambridge STT Overview P.C. Woodland, H.Y. Chan, G. Evermann, ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/woodland_earsfeb04.pdf23 Mar 2004: Eval03 with CU-HTK P1-P2 System. Overall Swbd Fisher Male Female. h5train03b LM03 24.6 28.7 20.2 25.7 23.5h5train03b LM03Fsh3896 23.9 28.2 19.3 ... 25.0 22.8fisher3896 LM03Fsh3896 23.1 27.0 18.9 24.6 21.6fisher3896h5 LM03Fsh3896 22.7 26.6 18.5 24.2 21.1. -
ICASSP04-v3.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/wang_icassp2004.pdf25 May 2004: Adaptation hypothesis true transCN (27.0). MLLR 27.7 27.0 26.1MMI-DLT 27.5 26.8 24.8MPE-DLT 27.3 26.9 23.2. -
Progress in Broadcast News English Transcription D.Y. Kim, M.J.F. ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/kim_sttmay04.pdf25 May 2004: 16 20 24 28. dev03 bnac 144 17.9bnacTDT4 375 16.8bnacTDT4TDT2 749 16.8 16.5 16.4bnacTDT4TDT2TDT4a 1126 16.7 16.3 16.0 16.1bnacTDT4TDT4a 752 16.7 -
Speaker Diarisation for Broadcast News S. E. Tranter† and ...
mi.eng.cam.ac.uk/reports/svr-ftp/tranter_odyssey04.pdf25 Mar 2004: This system gave a diarisation error of 24.46% on the develop-ment and 23.85% on the evaluation data. ... Adv Seg Clust Score MetricNONE CUED MIT 24.23 PrimaryCUED TDT4 MIT MIT 28.26 Secondary. -
paper.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/cipolla_bmvc04.pdf28 Jul 2004: 4] M. Fischler and R. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysisand automated cartography.Graphics and Image Processing, 24(6):381–395, 1981. -
RAO-BLACKWELLISED GIBBS SAMPLING FOR SWITCHING LINEAR…
mi.eng.cam.ac.uk/reports/svr-ftp/rosti_icassp2004.pdf22 May 2004: Togive an idea of the range of these N -best lists the oracle (best) er-ror rate on the tst data was 1.24% and the “idiot” (worst) errorrate was -
DEVELOPMENT OF THE CUHTK 2004 RT04F MANDARIN CONVERSATIONALTELEPHONE…
mi.eng.cam.ac.uk/~mjfg/rt04f_mandarin.pdf23 Dec 2004: Development data, dev04, was madeavailable for this task comprising 2 hours of data, 24 conversations.The 2003 evaluation data, taken from the LDC CallFriend data,eval03, was also used to evaluate ... The eval04 test set consists of about 1 hour of -
CAMBRIDGE UNIVERSITYENGINEERING DEPARTMENT Automatic Transcription…
mi.eng.cam.ac.uk/~mjfg/hain_tr465.pdf23 Dec 2004: Results were obtained by re-scoring of 4-gramlattices. Feature Transform Swbd1 Swbd2 Cellular Total— 24.2 40.8 40.4 35.1. ... The resulting 4-gram LM is further interpolated with a class-based trigram languagemodel where the classes are automatically -
Cluster Voting for Speaker Diarisation S.E.…
mi.eng.cam.ac.uk/reports/svr-ftp/tranter_tr476.pdf13 May 2004: 92 32.06 24.95Num Poss 27 9 3 (39)Best 19.94 36.46 31.74 24.68. ... miss Worst 31.96 37.96 32.06 27.44allowed Mean 24.63 37.45 31.95 25.83. -
2003ismar.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/klein03ismar.pdf11 Feb 2004: Tsai [24] introduces a rich camera model includingradial distortion and proposes a two-stage calibration tech-nique, consisting of an initial linear solution followed by anonlinear optimisation. ... Visual servoing-basedaugmented reality. In Proc. IEEE -
3D ULTRASOUND PROBECALIBRATION WITHOUT A POSITION SENSOR A. H. ...
mi.eng.cam.ac.uk/reports/svr-ftp/gee_tr488.pdf4 Sep 2004: top right 0.17 0.28 0.07 0.24 < 0.30bottom left 0.22 0.19 0.27 0.35 < 0.39bottom right 0.28 0.27 0.28 ... 3.5 MHz centre 0.24 0.43 0.33 0.14 < 0.43(12 cm) top left 0.43 0.55 0.55 0.49 < 0.75. -
CAMBRIDGE UNIVERSITYENGINEERING DEPARTMENT SWITCHINGLINEAR DYNAMICAL…
mi.eng.cam.ac.uk/reports/svr-ftp/rosti_tr461.pdf29 Jan 2004: The LDS belongs to the subset of state space models called linear Gaussian models [24]. ... Alternatively, the derivation may bedone completely using properties of conditional Gaussian distributions and matrix algebra [24]. -
CAMBRIDGE UNIVERSITYENGINEERING DEPARTMENT FACTOR ANALYSED HIDDEN…
mi.eng.cam.ac.uk/reports/svr-ftp/rosti_tr453.pdf26 Jan 2004: ĉ(o)jm =. T. t=1. M(x). n=1. γjmn(t). T. t=1. γj(t). (24). ... The 16 observation space component system achievedthe same performance as 24 component baseline system with 611 free parameters fewer.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.