Search

29 Apr 2004: Appendix - Cluster Voting Results by Show. System ABC VOA PRI NBC CNN MNB TOTALCUED-diary-bic (input 1) 32.03 20.78 21.40 32.06 37.92 10.74 ... 12CUED-diary-cost (input 2) 29.26 19.82 20.48 31.56 37.18 29.34 27.09Best CVOS score 26.71 18.43 18.11 29.84 37

14 Jun 2004: 43.60. CU. PER. 0.4. 0.2. 9.1. 11.60. 29.7. 32.20. MIT. CU. ... MIT. MIT. 2.3. 3.7. 5.6. 25.93. 20.6. 40.96. MIT. PER. 0.6.

25 May 2004: Gaussianisation. • Transform any distribution to standard Gaussian N(0, I). 20 15 10 5 0 5 10 15 200. ... Gaussianised 29.8 21.9 26.0CN 28.7 21.3 25.1. CNC 28.1 20.8 24.6. •

29 May 2004: Gauss 24.0 20.7 20.7 17.7 16.0WER (%) 35.3 35.1 35.2 35.3 35.5. ... Using the “opti-mal” structure, determined with α = 0 and 4 iterations of structureoptimization the error rate fell to 35.1% and the average numberof components per state was 20.7.

23 Mar 2004: Cluster-based mean and variance normalisation was used. • ML search for warp-factor done using parabolic search in the range [0.80,1.20]. • ... 20% parameters reduction. • 0.5%0.7% abs improvement over global HLDA system. •

25 May 2004: 0 5 10 15 20 25 3026. 26.5. 27. 27.5. 28. ... 0 5 10 15 20 2526. 26.5. 27. 27.5. 28. 28.5.

29 Apr 2004: 8#PFMs 10 td 70-30 28.8 29.1 18.5 19.5 47.3 48.6#PFMs 20 td 50-50 33.2 34.8 13.9 14.8 ... The DB98 SULMs reduce the DEL error by c.20% abs (while increasing the INSerror by c.20% abs) compared to the LDC SULMs.

21 Sep 2004: Fortunately a number of efficient approximate algorithms have been proposed suchas graph cuts [1] and belief propagation [20]. ... Szeliski. Layered depth images.Computer Graphics,32(Annual Conference Series):231–242, 1998. [20] J. Sun, H,-Y Shum, and N

25 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

25 May 2004: The testing adaptation isperformed on 1994 NAB Spoke 3 (s3-dev and s3-eval) task withan enrollment set (40 utterances) and a testing set (about 20 utter-ances) for each speaker.

4 Mar 2004: be estimated [20], whichremoves one degree of freedom in the ambiguities of the reconstruction. ... 12] M. Zerroug, R. Nevatia, Volumetric descriptions from a single intensity image, Int.Journal of Computer Vision 20 (1/2) (1996) 11–42.

18 Jun 2004: Bjik :=. ek ei 〈ej,V〉 (20). as boundary integral constants with V denoting the outward normal along. ... IEEE Trans. Image Processing 7 (1998) 398–410. 20. Schwarz, H.: Numerische Mathematik.

27 May 2004: CNC P4.[ACD]P5.[ACD] 24.1 17.1 20.7. Table 6. %WER on eval03 for all stages of 2003 system.

26 Jan 2004: 19). Σ̂(o). jm =1. PT. t=1 γ(o)jm(t). TX. t=1. γ(o)jm(t)diag. “. oto′. t (20). h. Ĉj µ̂(o)jm. i h.

11 Feb 2004: Next, control points are initialised at regular intervals(20 pixels) along every model edge. ... In Proc. IEEEIWAR’98, San Francisco, November 1998. [20] H. Rehbinder and B.

26 Jan 2004: 20). where diag() sets all the off-diagonal elements of the matrix argument to zeros. ... vectors have to beused in the covariance matrix update formula in Equation 20.

26 Nov 2004: 3 METHOD 9. 5 10 15 20 25 30 35 40 45 5020. ... Multiparametric attenuation andbackscatter images for characterization of carotid plaque. Ultrasonic Imaging 22 (1), 20–34.

24 Aug 2004: 2002). Ultrasound images are acquired at 20-30Hz, along with theirlocation and orientation in space. ... ki from eq. (2) was calculated for all 190 pairs of the 20 scans.

25 Mar 2004: CNN had less smoothing than the otherTV sources due to the frequent occurrence of 20 to 30s longsports reports between adverts and station jingles. ... MIT MIT 2.3 3.7 5.6 25.93 20.6 40.96MIT PER 0.6 1.4 9.2 12.54 25.1 28.49.

29 Jan 2004: Approximate Viterbi algorithm keeps only the path with the highest log-likelihoodactive [20]. ... 0 20 40 60 80 1008.7. 8.75. 8.8. 8.85. 8.9. 8.95.

13 May 2004: 10. 20. 30. 40. 50. 60. 70. Number of Words Spoken by Speaker. ... Show # Resegments SuperGroupsTotal Non-Conflicting [ID/ Duration(s)/ # resegments]. ABCWNT 18 18 -VOAENG 18 12 [g0/30.23/2], [g1/170.86/2], [g2/43.46/2]PRITWD 20 20 -NBCNNW

4 Sep 2004: uncertainty in TSG 0.90 mm 0.71 mm 0.65 mm 0.63 0.61 1.20. ... The focus was set at 20 mm whenimaging the top wedge-pair and 97 mm for the bottom wedge-pairs.

22 May 2004: Nine full iterations of embedded training were used with 20 withiniterations and 20 row by row transform iterations (Gales, 1999). ... matrix. Nine full iterationsof embedded training were used, each with 20 within iterations.

26 Jan 2004: 10. 5. 0. 5. 10. 15. 20. 20 15 10 5 0 5 10 15 2020. ... 15. 10. 5. 0. 5. 10. 15. 20. 20 15 10 5 0 5 10 15 2020.

8 Oct 2004: 2.5.1 Covariance Matrix Modelling 18. 2.5.2 Precision Matrix Modelling 20. 2.6 Segment Models 21. ... to reduce boundary effects [20] in the subsequent processing. The fast Fourier transform is.