Search

26 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.

26 Jan 2004: The likelihood of an observation given thestate is simply. p(oj|x) = N(oj; Cx µ(o), Σ(o)) (24).

29 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].

11 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

22 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

23 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.

25 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.

29 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

13 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.

22 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