Search

10 Dec 2003: 5MPE fisher3896 (520h) MPE 26.4 30.5 22.1 28.3 24.6MPE fisher3896h5 (880h) MPE 25.7 29.9 21.3 27.4 24.1. ... 3 25.0 22.8fisher3896 LM03Fi 23.1 27.0 18.9 24.6 21.6fisher3896h5 LM03Fi 22.7 26.6 18.5 24.2 21.1.

19 Sep 2003: Fig. 1. Test set word error rate for all possible models, with thestandard front-end 12, 16 and 24 component performance. ... The best perfor-mance, 36.8%, was obtained using 24 components per state and anHLDA projection from 52 dimensions to 38

23 Jun 2003: 0 26.1 23.7P3.3-cn 20.4 24.3 26.6 24.0final 19.9 23.5 25.8 23.3. ... 320xRT 2002† 19.8 24.3 27.0 23.910xRT 2002† 22.3 27.7 31.0 27.2 14%.

29 Nov 2003: Object View! normalised 24 2 4 H H #cube. Z n @ D$L Z¡ LD ' n$ $ n[ D[ n[ ' D ¡¢ J n D Z n D @ n L 3LD Z ... variousimages! normalised is expectedto beapproximatelyone. Note that the variationsin. H H are much larger then variationsin 24 2

24 Jul 2003: CNC P4.[123]P5.[123] 19.8 24.3 27.0 23.9%WER on eval02 for all stages of 2002 system, manual segmentation. • ... Final NCE is 0.318. Cambridge UniversityEngineering Department. Rich Transcription Workshop 2003 24.

23 Sep 2003: System A B C D23.0 23.6 23.4 24.8. A 23.1 22.6 22.7B 22.9 23.3C 22.8. ... full ’02 19.8 24.3 27.0 23.910x ’02 22.3 27.7 31.0 27.2 14%.

16 Sep 2003: CambridgeUniversityEngineeringDepartment. EARSMeetingSept20037. X.Liu&M.J.F.Gales:AutomaticModelComplexityControlUsingMarginalizedDiscriminativeGrowthFunctions. IssueswithMLparadigm.

12 May 2003: This paper presents a methodfor hand tracking that estimates the pose of a 3D hand modelconstructed from truncated quadrics by using an UnscentedKalman filter [18, 24]. ... Originally published in1952. [24] E. A. Wan and R. van der Merve.

23 Jun 2003: Automatic Segmentation. Segmentation Diarisation CER (%)MS FA Tot. Manual 1.2 24.5 25.6 49.8Automatic 3.7 8.3 11.9 50.8.

25 Sep 2003: j (τ ) = γnum. j (τ ) γden. j (τ ) Cp(O, Sj,τ |Θ̃) (24). ... For more details see [15]. Two globalcomplexity attributes of a single transform HLDA system wereoptimized: the number of Gaussian components per state from therange {12, 16, 24}; the

8 Jul 2003: Disfluency Results. System Edit (BN=84,CTS=521) Filler(BN=143,CTS=840) Total( Context? ) Miss FA Error Miss FA Error ErrorBN-ASR () 91.67 28.57 120.24 48.95 ... 87.41 136.36 130.40BN-ASR (X) 91.67 15.48 107.14 48.95 82.52 131.47 122.47BN-REF () 83.33

22 Jul 2003: CU-DIARY 0.2 9.1 24.0 33.29 2.1 1.5 5.9 9.5MIT-DIARY 2.7 5.6 16.1 24.46 2.8 1.7 ... 1 24.23 2.6 24.7 2.1 43.60PERF 0.2 9.1 0.4 11.60 0.2 29.7 0.4 32.20.

5 Dec 2003: CACM, 24(6):381–395, June 1981. [6] C. Harris and M. Stephens. A combined corner and edge detector.

24 Jul 2003: Lattice-Regen 14.4 8.5 15.1 17.7 16.9 14.6 21.3 24.4 14.5 13.8.

19 May 2003: 3.4 100 (6.5, 4.6, -15.3) 3.4 100 (7.7, 2.1, -15.3) 4.0arm 30 100 (24.3, -5.1, -9.3) 5.1 100 ... With the full search range,the low resolution search finds a false minimum absolute difference at offset (8, 48, 24) pixels(in dividing plane coordinates).

10 Dec 2003: Results of pairwise system combination using CNC:. System A B C D23.0 23.6 23.4 24.8.

20 Oct 2003: D12DT12. ]1. D12 a (24). The Euclidean projection matrix E1 can then be rebuilt toexactly satisfy the constraint by.

16 Sep 2003: MPron 6447 8.97 9.65 9.33SPron1 6419 9.05 9.95 9.53SPron2 6425 9.33 9.93 9.64SPron3 6486 9.65 10.95 10.24. ... Discriminative pronunciation selection. Cambridge UniversityEngineering Department. EARS STT Meeting Martigny 2003 24.

12 May 2003: Belongie,J. Malik, and J. Puzicha. Shapematchingandobjectrecognitionusingshapecontexts. IEEE Trans.PatternAnalysisand Machine Intell., 24(4):509–522,April 2002.

24 Jul 2003: PFM N/A 24.88 43.98 54.61 123.47SULM bg N/A 81.30 6.32 3.56 91.19.

5 Dec 2003: If enough epipolar tangencies are available, the epipolar geometry can be estimatedand hence the motion can be determined up to aprojective transformation [23,24].The intrinsic parameters [17] of the cameras ... 563–578. [24] R. I. Hartley, Estimation

5 Dec 2003: fewer parameters than a setof 24 3D points in general position.

17 Jan 2003: 0 9.9 17.5 24.1 18.7 17.1 20.4 29.4 16.6 16.6MPE 16.2 9.6 17.1 22.6 17.5 16.1 ... Cambridge UniversityEngineering Department. EARS Workshop Jan 2003 24. Woodland et al.: HTK Experiments on BN and CTS. •

23 Nov 2003: 6] M.A. Fischler and R.C. Bolles.Random sample consensus: A paradigm for model fitting withapplications to image analysis and automated cartography.CACM, pages 24(6):381-395,June 1981.

18 Dec 2003: 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

18 Sep 2003: can then be used to recover the relative motion [23], [24]. ... 293, pp. 133–135, September 1981. [24] O. D. Faugeras, “What can be seen in three dimensions with an uncalibrated stereo rig,” in Proc.

5 Dec 2003: rotation [24] or planar motion [25]. The calibration technique introduced in this paper, namelycalibration from surfaces of rev-. ... August 27, 2002 DRAFT. 24 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL.

9 Oct 2003: An Investigation into the Interactions betweenSpeaker Diarisation Systems andAutomatic Speech Transcription. †S.E. Tranter, †K. Yu, ‡D.A. Reynolds, †G. Evermann,†D.Y. Kim & †P.C. WoodlandCUED/F-INFENG/TR-464. 9th October 2003. †

5 Dec 2003: #"$%& '%( ) ,-./01 23. 465785:9<;>=@?ACB DE5:FG5:H:5:IKJMLNLPO 7Q5SR;UT:JMVWVYXZA. [:S]_ acb>d]ce)bSf ghei jke]']_a>jkeimlone)jqpN]_acrWjqbUsf gutNdKvma>jqw)iN]xlotyxdzv)a>jqw)iN]Nlot{:|2}MlnSK]_acb>d]_e)bf gutfNdE)bWjkei)loSNgf acw-{.acf@f