Search
Search Funnelback University
301 -
350 of
1,000
search results for katalk:za33 24 |u:mi.eng.cam.ac.uk
where 0
match all words and 1,000
match some words.
Results that match 1 of 2 words
-
ITERATIVE UNSUPERVISED ADAPTATION USING MAXIMUMLIKELIHOOD LINEAR…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_icslp96.pdf17 Oct 2000: 704/c 26.3 15.570a/b 10.3 1.970f/d 18.8 7.670w/c 24.2 15.8. Table 1: Lattice error rates for several development test speakerswith ... a fg 14.24 —HMM-2 thresh. b fg 13.81 —HMM-2 thresh. c fg 13.71 6.68. -
Regularised marching tetrahedra:improved iso-surface extraction G.M.…
mi.eng.cam.ac.uk/reports/svr-ftp/treece_tr333.pdf20 Dec 1999: Triangulation Each sample point is surrounded by 24 tetrahedra, and each tetrahedronis associated with 4 sample points. ... Computer GraphicsForum, 15(4):191–203, 1996. [24] G. M. Treece, R. W. Prager, A. -
Augmented Statistical Models for Classifying Sequence Data Martin…
mi.eng.cam.ac.uk/~mjfg/thesis_ml362.pdf16 Jan 2008: 2.2.2 Hidden conditional random fields (HCRFs). 24. 2.2.3 Parameter estimation for conditional models. -
Stimulated Deep Neural Network for Speech Recognition
mi.eng.cam.ac.uk/~mjfg/interspeech16_stimu.pdf26 Sep 2016: IEEE, 2011, pp.24–29. [9] R. Gemello, F. Mana, S. Scanzio, P. -
Metadata Extraction at Cambridge University Sue Tranter, Marcus…
mi.eng.cam.ac.uk/research/projects/EARS/pubs/tranter_earsjan03.pdf8 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 -
BI-DIRECTIONAL LATTICE RECURRENT NEURAL NETWORKSFOR CONFIDENCE…
mi.eng.cam.ac.uk/~mjfg/ALTA/publications/ICASSP2019_li.pdf31 Aug 2019: may include embeddings [24], acoustic andlanguage model scores and other information. ... 24] T. Mikolov, I. Sutskever, K. Chen, S. S. Corrado, and J. -
Improving Speech Recognition and Keyword Searchfor Low Resource…
mi.eng.cam.ac.uk/~mjfg/interspeech15-mendels-babel.pdf9 Oct 2015: Telugu. VLLP 0.838 57.0Blogs 0.128 2625.6News 0.000 893.0Subtitles 0.024 24.9TED 0.000 18.8. ... 24] Z. Tüske, J. Pinto, D. Willett, and R. Schlüter, “Investigation oncross- and multilingual MLP features under matched and mis-matched acoustical -
Segment Generation and Clustering in the HTKBroadcast News…
mi.eng.cam.ac.uk/reports/svr-ftp/hain_darpa98.pdf8 Mar 2000: M S T. M 82.11 17.89 0.00N 15.27 84.22 0.51S 0.56 98.24 1.20T 0.00 1.19 98.81. -
ESTIMATION OF DISPLACEMENTLOCATION FOR ENHANCED STRAIN IMAGING J. E.…
mi.eng.cam.ac.uk/reports/svr-ftp/lindop_tr550.pdf30 Mar 2006: Examples includequasistatic compression imaging [26, 29], axial shear wave imaging [32] and acoustic radiationforce imaging in both quasistatic/impulsive [24] and dynamic [2] forms. ... We substitute this into Equation 24, and rearrange to produce a -
PHONETIC AND GRAPHEMIC SYSTEMS FOR MULTI-GENRE BROADCASTTRANSCRIPTION …
mi.eng.cam.ac.uk/~mjfg/ALTA/publications/ICASSP2018_YuWang.pdf12 Sep 2018: 23] L. Breiman. Bagging predictors. Machine learning,24(2):123–140, 1996. [24] O. Siohan, B. ... IEEE/ACM Transactions on Audio, Speech,and Language Processing, 24(8):1438–1449, 2016. Introduction. Graphemic English systems. -
DISCRIMINATIVE CLASSIFIERS WITH ADAPTIVE KERNELS FOR NOISE ROBUST…
mi.eng.cam.ac.uk/~mjfg/gales_flego_CSL10.pdf14 Sep 2010: yt µ. (ωjM)y. ). . (24). where the clean models have been compensated for the test condition Y,λ = {λ(ωl)y , λ(ωj)y }, and there are a total of ... 05 8.78 8.43 6.20 9.53 8.22. 00 -
STIMULATED TRAINING FOR AUTOMATIC SPEECH RECOGNITION ANDKEYWORD…
mi.eng.cam.ac.uk/~mjfg/CUED-Ragni-Stimulated-ASR-KWS.pdf22 Mar 2017: These weretrained on FLP data of 24 Babel languages and CTS data of 4 addi-tional languages, English, Spanish, Arabic and Mandarin, releasedby LDC. ... Stacked Hybrids were trained withand without stimulated training using monophone initialisation -
stenger_imavis06.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/stenger_imavis06.pdf21 Sep 2006: 21] for upper bodypose estimation. In [24] it is suggested to partition the parameter spaceof a 3D hand model using a multi-resolution grid. ... range. At detection rates of 0.99 the false positiverate for the centre template is 0.24, wheras it is -
Joint Decoding of Tandem and Hybrid Systems for Improved ...
mi.eng.cam.ac.uk/~mjfg/interspeech15-wang-babel.pdf9 Oct 2015: Acoustic likelihood combination and lat-tice combination have been compared in [24]. ... Speech and Audio Processing, vol. 2, no. 1,pp. 217–223, 1994. [24] P. -
SPOKEN DOCUMENT RETRIEVAL FOR TREC-7 AT CAMBRIDGE UNIVERSITY S.E. ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_trec7.pdf8 Mar 2000: This system gave a word error rate of 24.1% on. the TREC-6 test data. ... 1 77.3 17.5 5.2 5.9 28.6HTK-2 80.8 14.6 4.6 4.9 24.1. -
Model-Based Approaches to HandlingUncertainty M.J.F. Gales Abstract A …
mi.eng.cam.ac.uk/~mjfg/noise_review10.v1.pdf3 Sep 2010: This chap-ter examines approaches that handle background-noise and channel distortions bymodifying the parameters of the underlying acoustic models, in this case HiddenMarkov Models (HMMs) [52, 24]. ... Though intuitively well motivated, from (24) it can -
tech.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/hsu_tr584.pdf5 Sep 2008: µPRA = pW TWS TSI TspI′. (24). This is a measurement of system accuracy, and includes errors from every component of thesystem. -
Imaging the femoral cortex: thickness,density and mass from clinical…
mi.eng.cam.ac.uk/reports/svr-ftp/treece_tr665.pdf29 Apr 2011: Any systematic measurementbias that affects the baseline and 24 month density estimates to different degrees will manifest themselvesas false thickness effects. ... In this instance, thereis a known source of bias: the 24 month scans extended, on average, -
PhD Thesis
mi.eng.cam.ac.uk/~mjfg/thesis_kcs23.pdf16 Nov 2007: 2.3 Limitations of HMMs for Speech Recognition 24. 2.3.1 Explicit Temporal Correlation Modelling 25. -
Optimisation of Fast LVCSR Systems Gunnar Evermann, Phil Woodland ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/evermann_stthomas03.pdf10 Dec 2003: Results of pairwise system combination using CNC:. System A B C D23.0 23.6 23.4 24.8. -
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. -
D:/docs/reports/tech_17/tech_17.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/treece_tr691.pdf4 Aug 2014: 0.3 t < 1.0 1.06 0.37 2.35 1.46 0.58 1.07 0.24 0.14 0.15 0.23 0.04 0.31. ... 0.3 t < 1.0 2 31 24 60 2 35 3 30 3 30 3 30. -
TextonBoost: Joint Appearance, Shape andContext Modeling for…
mi.eng.cam.ac.uk/reports/svr-ftp/shotton_eccv06.pdf15 Feb 2006: For cases like these, the algorithm of [24] couldbe used to refine the class labeling. ... In: AAAI.(2005) 1508–1513. 24. Kumar, S., Hebert, M.: A hierarchical field framework for unified context-basedclassification. -
LARGE SCALE MMIE TRAINING FOR CONVERSATIONALTELEPHONE SPEECH…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_stw00.pdf5 Oct 2000: Lattices were generated on the training set using a bigramLM. The bigram 1-best hypotheses had a 24.6% word error rate(WER) and a Lattice WER (LWER) of 6.2%. -
Knill_CUEDSeminar_20140403.dvi
mi.eng.cam.ac.uk/~kmk/presentations/CUED_Apr14_Knill.pdf12 May 2016: CUED Lorelei Team. Babel ProgramSeminar at Cambridge University April 2014 24. -
4F12-notes-2.dvi
mi.eng.cam.ac.uk/~cipolla/lectures/4F12/Slides/4F12-notes-2.pdf7 Oct 2023: outliers in the output of the corner detector. 24 Engineering Part IIB: 4F12 Feature extraction. -
Investigation of multilingual speech-to-text systems for use in…
mi.eng.cam.ac.uk/~kmk/presentations/UEdin_Feb14_Knill.pdf12 May 2016: CUED Lorelei TeamBABEL Program. Seminar at Edinburgh University February 2014 24. -
SENSORLESS RECONSTRUCTIONOF UNCONSTRAINED FREEHAND 3D ULTRASOUND DATA …
mi.eng.cam.ac.uk/reports/svr-ftp/housden_tr553.pdf22 May 2006: Communications of theACM, 24(6):381–395, 1981. 15. [5] A. H. Gee, R. ... H. Berman. Engineering a freehand 3Dultrasound system. Pattern Recognition Letters, 24:757–777, 2003. -
The Cambridge University March 2005 Speaker Diarisation System R. ...
mi.eng.cam.ac.uk/reports/svr-ftp/sinha_eurospeech05.pdf23 Jun 2005: 15. 16. 17. 18. SID CLR Threshold. Dev. 24 D. ER. ... Seg. men. t Im. pu. rity. on. dev. 04 (. 24 s. -
Kate Knill ALTA Institute, Cambridge University Engineering…
mi.eng.cam.ac.uk/~mjfg/ALTA/presentations/Knill_ISCSLP_Keynote_2022.pdf19 Jan 2023: 24. GEC. 25. seq2seq GEC. Treat GEC as a machine translation problem i.e. -
Interactions Between Diarisation and STT Sue Tranter1, Kai Yu1, ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/tranter_rt03sinter.pdf22 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. -
HYBRID SYSTEMS FORRECONSTRUCTION OF FREEHAND 3D ULTRASOUND DATA R. ...
mi.eng.cam.ac.uk/reports/svr-ftp/housden_tr574.pdf30 Mar 2007: In theplane of the images, the offset is found using standard image registration and motion trackingtechniques [2, 24]. -
Prediction of Total and Regional Body Composition from 3D ...
mi.eng.cam.ac.uk/~cipolla/publications/article/2024-4-Body-composition.pdf23 Apr 2024: More recently, Leong et al. [24] use a variational autoencoder(VAE) [20] to learn latent DXA encoding, and map 3DO scans to pseudo-DXA images. ... Mean bias was 0.24 (6.7; 6.2)% for percentage body fatand for the other body composition metrics, the mean -
Estimation of Epipolar Geometry from Apparent Contours: Affine and…
mi.eng.cam.ac.uk/reports/svr-ftp/mendonca_contours.pdf10 Aug 1999: F =. 24 0 0 c0 0 da b e. 35 : (4). ... F =. 24 0 0. 0 sin0. 0 0 0 cos0sin cos p1 2 02. -
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 -
Learning Discriminative Canonical Correlationsfor Object Recognition…
mi.eng.cam.ac.uk/reports/svr-ftp/kim_eccv06.pdf21 Sep 2006: Pattern Recognition Letters, 24(2003):2743–2749, 2003. 8. O. Yamaguchi, K. Fukui, and K. -
Boosted Manifold Principal Angles for Image Set-Based Recognition…
mi.eng.cam.ac.uk/~cipolla/publications/article/2007-PR-Kim.pdf13 Mar 2018: recognition from face motion manifolds.Image and Vision Computing, 24(5),. 2006. (in press). ... 24] R. O. Duda, P. E. Hart, and D. G. Stork.Pattern Classification. -
High resolution cortical thickness measurement from clinical CT data…
mi.eng.cam.ac.uk/reports/svr-ftp/treece_tr634.pdf12 Jan 2010: 21 0.78464 1.10 1.05 0.47 0.75 0.10 0.54 0.05 0.55465 0.95 1.18 0.24 0.96 0.02 0.68 ... 70 0.22 0.54 0.19 0.54all 1.24 0.83 0.19 0.62 0.01 0.48 0.01 0.47. -
AN INTELLIGENT INTERFACEFOR FREEHAND STRAIN IMAGING J. E. Lindop, ...
mi.eng.cam.ac.uk/reports/svr-ftp/lindop_tr578.pdf25 May 2007: imaging was first tested clinically for breast scanning [4] and breast screeninghas ever since been a key driver for research [7, 23, 24]. ... Berman. Engineering a freehand 3D ultrasound system.Pattern Recognition Letters, 24(4–5):757–777, February -
DYNAMIC RESOLUTION SELECTIONIN ULTRASONIC STRAIN IMAGING J. E.…
mi.eng.cam.ac.uk/reports/svr-ftp/lindop_tr566.pdf29 Sep 2006: 1.24. 1.26. 1.28. 1.3. 1.32. 1.34x 10. 3. scatterer depth (m). ... f) Window length (max=175), strain and SNRe forDRS, SNRe=12.87 and V=5.24. -
3D ELASTOGRAPHYUSING FREEHAND ULTRASOUND J. E. Lindop, G. M. ...
mi.eng.cam.ac.uk/reports/svr-ftp/lindop_tr531.pdf28 Jul 2005: Alam et al. [24] among others have noted that speckle tracking inthis form is suboptimal for elastography, because tissue compression causes both displacements(which are estimated) as well as within-window -
Overview - 2007
mi.eng.cam.ac.uk/~cipolla/archive/Presentations/2007-Cipolla-Vision.pdf19 May 2014: 1) (2) (3) (4). (9)(8)(7)(6). (5). (24). Learned contour and texture. -
sig-004.dvi
mi.eng.cam.ac.uk/~mjfg/mjfg_NOW.pdf19 Mar 2008: Foundations and Trends R inSignal ProcessingVol. 1, No. 3 (2007) 195–304c 2008 M. Gales and S. YoungDOI: 10.1561/2000000004. The Application of Hidden Markov Modelsin Speech Recognition. Mark Gales1 and Steve Young2. 1 Cambridge University -
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 -
Discriminative Complexity Control and Linear Projections for Large…
mi.eng.cam.ac.uk/~mjfg/thesis_xl207.pdf16 Nov 2007: 2.5 HLDA and LDA projection 24. 2.6 multiple HLDA projections 25. -
Model-based Approaches to Robust SpeechRecognition in Diverse…
mi.eng.cam.ac.uk/~mjfg/thesis_yw293.pdf27 Oct 2015: 21. 2.3.3.2 Discriminative Training. 24. 2.4 Recognition of Speech Using HMMs. ... Normally,. a truncated DCT transform is used, i.e., Lc( 13) is smaller than Lf ( 24) and the high ordercepstral coefficients are discarded. -
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. -
lf3.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lum.pdf11 Nov 2005: 1994). Dynamic be-lief networks for discrete monitoring. IEEETransactions on Systems, Man, and Cybernet-ics, 24(11):1593{1610. -
Combining Single View Recognition and Multiple View Stereo For ...
mi.eng.cam.ac.uk/reports/svr-ftp/dick_iccv01.pdf5 Dec 2003: fewer parameters than a setof 24 3D points in general position. -
A Statistical Consistency Check for the SpaceCarving Algorithm. A. ...
mi.eng.cam.ac.uk/reports/svr-ftp/broadhurst_cipolla_bmvc2000.pdf25 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
Refine your results
Date
- 454 2018
- 124 2005
- 40 2000
- 33 2006
- 29 2003
- 26 2023
- 25 2022
- 24 Past year
- 21 2004
- 20 2014
- 20 Uncertain
- 18 2007
- 17 2019
- 17 2016
- 17 2015
- 15 2009
- 14 2010
- 14 2024
- 13 2008
- 12 2017
- 12 2001
- 11 2013
- 10 2021
- 10 2020
- 9 2012
- 7 Past 3 months
- 7 Past 6 months
- 7 2002
- 6 2011
- 6 1999
- 2 Past month
- 1 Past week
- 1 Yesterday
- 1 Past fortnight
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.