Search

7 Oct 2001: The overall word error rate for the data was 24.8%, the lowest in the TREC-7 SDR evaluation, with the baselines provided by NIST offering 33 and 42%. ... The final project publications include the TREC-9 paper [24] , two papers in the International

23 Feb 2002: 183k articles in [24]), in previous work we found that increasing the parallel corpus size to approximately 110k articles did not help performance [16]. ... 45.02. cr-limsi2. 21.2. 37.24. 39.28. 41.62. 44.12. cr-limsi1. 21.5. 36.56. 38.57.

30 Mar 2000: 24.7. 35.5. 10181. Windowing - 30s@15s. 33.9. 46.1. 18669. Windowing - 30s@10s. ... 55.73. 52.75. 43.89. ----. Sheffield. 32.0. 44.7. 60.66. 52.85. 42.47. 38.24.

19 Apr 2000: 39.39. 27.42. 752913. -. -. N. B. 95.8. 37.52. 24.92. 698461. -. -. ... In Proc. TREC-7, NIST SP 500-242, pages 1-24, Gaithersburg, MD.

17 Nov 2017: Decoder Gujarati Mixed(word) %PER %GER %PER %GER. Ph 25.8 24.9 33.9 32.9Gr 29.0 23.7 36.6 30.8.

20 Nov 2017: I All models used 24 log-Mel filter bank coefficients with their and values as input features, except the CNN which used40 without any.

12 Apr 2005: 302k 9k+ 16.0 13.9 24.8 –MLE 415k 9k+ 16.0 13.5 24.3 –. 398k 12k+ 16.1 13.6 24.5 –. 302k 9k+ 13.2 11.2 ... dev04 eval03 dev04f. MLEMPron 16.0 13.6 24.5SPron 15.6 13.5 24.2. MPEMPron 12.9 11.1 19.1SPron 12.7 10.8 18.8.

23 Dec 2017: Table 1: Performance classifying; happy, sad, angry, neutral. Model Inputs AccuracyRandom N/A 24.14%Most common N/A 33.00%LSTM eGeMAPS LLDs 43.17%TD-CNN Spectrogram

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.

12 Apr 2005: S1 6K (28)0. 34.1 26.0 30.2 26.4S4 9K (36). (ML)33.0 24.8 29.0 25.3. ... 32.3 22.9 27.8pMPEMPE 35.1 26.0 30.7 33.2 24.1 28.8 32.9 23.6 28.4.

10 Oct 2001: X) 64.95 61.25 46.82 45.24 44.27 30.33 39.98 42.14 38.65 35.72 BE DBRF2 (X) 66.57 65.89 45.21 ... BE DBRF (X) 69.41 69.12 52.55 51.73 51.14 36.86 41.99 44.13 42.14 42.05 BE [PR]BRF (A) 66.24 64.53

5 Jun 2002: 16 20 24 2833. 33.5. 34. 34.5. 35. 35.5. 36. 36.5. ... Cambridge UniversityEngineering Department. Rich Transcription Workshop 2002 24. Woodland, Evermann, Gales, Hain, Liu, Moore, Povey & Wang: CU-HTK April 2002 Switchboard system.

19 May 2005: Systemeval03. dev04s25 fsh Avg. P2-cn HLDA 26.6 18.4 22.6 18.7. P3a-cn SAT 24.5 17.1 20.9 17.3P3c-cn SPron 24.7 ... cn SPAM 24.1 16.9 20.6 17.2P3h-cn SATSPAM 23.9 16.9 20.5 16.8P3i-cn CTRL 24.5 17.5 21.1 17.6.

27 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.

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

15 Feb 2005: 18.5. 19. 19.5. 20. mea. n D. ER. on. all. 24 d. ... RT-04f RT-04f RT-04f 23.86 24.12† Official evaluation submission. • New segmenter and clusterer resulted in 14% absolute drop in primary DER. •

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 Mar 2005: shows. The DER is 24.16%(28.05%) if the best(worst) input istaken independently for each show. ... true reference speakers, so when scoringagainst the reference, the supergroups may no longer be treated indepen-dently thus dramatically increasing the

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

20 Jan 2007: Test set baseline N-gram adaptfixed weights dynamic weights. dev05bcm (BC) 25.6 24.5eval04 (BN) 14.7 14.8dev04f (BN) 6.4 6.5. ... P3 27.4 25.6 24.5 24.3 24.3. Table 3: P2, P3 stage dev05bcm CERs.

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

29 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.

25 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. •

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.

8 Mar 2000: This system gave a word error rate of 24.1% on the TREC-6 test data and ran in about 50 times real time. ... Recogniser WER stop map stemIBM Baseline 50.0 47.5 47.2 44.3Sheffield 39.8 37.6 37.1 34.6HTK-1 28.6 24.9 24.7

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

26 Mar 2005: 12.5. 13. 13.5. 14. 14.5. 15. SID Threshold. Dev. (24. sh. ... 11. 11.5. 12. 12.5. 13. SID Threshold. Eva. l (24. sh.

29 Apr 2006: average 92.0 64.1 58.3 17.0std 7.8 9.2 24.3 8.8. video sequences of the person in arbitrary motion (signif-icant translation, yaw and pitch, ... cluded and expression variant faces from a single sample per class.PAMI, 24(6), 2002.

10 Apr 2000: M S TM 82.11 17.89 0.00N 15.27 84.22 0.51S 0.56 98.24 1.20T 0.00 1.19 98.81. ... 1F3 36.4 32.7 35.3 33.9F4 28.6 25.0 25.4 24.4F5 28.6 23.8 27.1 26.5FX 58.5 55.2 56.8

8 Mar 2000: Y 14.2 8.0 15.4 20.3 16.5 14.0 16.6 24.6. ... ROVER fgintcat 4/Y1/N 13.8 7.8 15.1 20.1 15.8 13.6 16.6 24.1.

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

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

27 Apr 2001: Ultrasound in Medicine and Biology, 24(6):855–869, 1998. [6] W. L. Smith and A. ... Parker. Multilevel and motion model-based ultrasonicspeckle tracking algorithms. Ultrasound in Medicine and Biology, 24(3):427–441, 1998.

10 Jan 2005: show. (b) Mean DER across all 24 development shows whenonly including c0 in clustering if the mean value is above a criticalthreshold. ... RT-04 RT-04 RT-04 23.86 24.12. Table 12. Progress since RT-03s on theeval04f data.

10 Aug 1999: 35 and P02 =. 24. a11 a12 a14 a13a21 a22 a24 a230 0 0 a33. ... F =. 24. 0 0 a24a330 0 a14a33. a24a11 a14a21 a24a12 a14a22 a24a13 a14a23.

15 Feb 2005: 0.16 0.18 0.2 0.22 0.24 0.2612. 14. 16. 18. 20. 22. ... Cambridge UniversityEngineering Department. RT04 EARS workshop 24. Recent Developments at Cambridge in Broadcast News Transcription.

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%.

8 Mar 2000: 22. 23. 24. 25. 26. 27. 28. 29. 30. 0 5 10 15 20 25. ... Comparing Table 4 with Table 3the advantage of including two passes can clearly be seen: onBNeval98 the error rate was reduced by 24% while the overallcomputation was increased by about a

8 Aug 2005: Both, centretemplateandmarginalizedtemplateshow betterclassificationperfor-mancethanthe trainedclassifier, in particular in the high detection range.At de-tectionratesof 0.99 thefalsepositive ratefor thecentretemplateis 0.24, wherasitis 0.64for

10 May 2000: ID BASE BRF UBRF3k 22.2 24.4 33.37k 33.8 37.5 44.3. 14k 41.4 47.6 51.827k 43.0 49.7 53.855k 43.5

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.

27 Jul 2020: CBCT non-planarity 2.47 2.46 3.35 15.7 16.0 14.8 12.1 10.8 8.63reach 9.36 9.16 9.57 26.7 24.7 ... MDCT non-planarity 3.04 3.67 4.52 15.1 14.2 15.5 11.7 10.6 8.3reach 13.6 11.2 10.4 26.3 24.1

13 Nov 2008: IEEE Transactions on MedicalImaging, 23:153–163, 2004. [24] A. Pesavento, C. Perrey, M. ... Ultrasound in Medicine and Biology, 24:427–441, 1998. [31] R. Zahiri-Azar and S.

8 Mar 2000: 36.5F4 24.2 25.1 23.1 21.3F5 25.7 24.1 25.9 23.0FX 57.2 53.7 57.1 50.4. ... 24.1 29.9ROVER BN2/3/gd ic 1/4 15.8 9.4 15.2 19.5 26.9 19.4 22.1 29.1.

10 Aug 2010: The individual image frames arelocated in space by a position sensor attached to the probe [16] or, in the case of intravascularimaging, by a continuous pullback method [24]. ... Communications of theACM, 24(6):381–395, June 1981. [10] T. G. Fisher, T.

19 Sep 2006: Cambridge University Press, 1999. [FB81] FISCHLER M., BOLLES R.: Random sample consensus:A paradigm for model-fitting with applications to image analysisand automated cartography.CACM 24, 6 (1981), 381–395.

25 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.

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

1 Apr 2005: Using improved acoustic/language models andby combining systems with different segmentations, the 10RTsystem gave on average a 24% relative reduction in WER over theRT03 system.

25 Oct 2000: Figure 2: Resultsfrom the existing SpaceCarving algorithm using different thresholdsettings. The voxel array size was , and the thresholdswere 48,32,24,16(of 255)respectively. ... Figure 4: Resultsfrom the existing SpaceCarving algorithm using different