Search
Search Funnelback University
- Refined by:
- Date: 2009
1 -
23 of
23
search results for news |u:mi.eng.cam.ac.uk
Fully-matching results
-
Machine Intelligence Laboratory : AGILE Overview
mi.eng.cam.ac.uk/research/projects/AGILE/index.html7 Oct 2009: Unsupervised Training for Mandarin Broadcast News and Conversation Transcription. ... Progress in the CU-HTK Broadcast News Transcription System. -
is2008.dvi
mi.eng.cam.ac.uk/~mjfg/raut_INTER08.pdf2 Mar 2009: 1. IntroductionSpeech recognition systems are increasingly being built withfound data such as broadcast news and conversational tele-phone speech recordings. ... Given this new set of MLLR trans-forms and the current DMT, a new DMT is estimated -
Ultrasound Deconvolution Project
mi.eng.cam.ac.uk/research/projects/Deconvolution_Of_3D_Ultrasound/20 Mar 2009: We will compare our new algorithms with segmentations performed by doctors to evaluate their performance. ... Through this project we will open up a new era of clearer, higher-resolution, cheap, safe, ultrasound imaging. -
report.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/ijaz_tr635.pdf20 Aug 2009: Step 2 (Reflection): Generate a new vertex xr by reflecting the worst point according to. ... Theparticle moves toward a new position according to Eq. (12) affected by the coefficients c and. -
Learning to Track with Multiple Observers Björn StengerComputer…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2009-CVPR-hand-trackingpdf28 Jul 2009: At each frame a new weak classifier islearned and the ensemble is updated by replacing the leastreliable classifiers in each time step. ... A new framework wasproposed that evaluates the robustness and precision of ob-servers, allowing the user to choose -
Context Dependent Language Model Adaptation X. Liu, M. J. ...
mi.eng.cam.ac.uk/~mjfg/liu_INTER08.pdf2 Mar 2009: An im-portant part of this new approach is obtaining robust estimation.Two schemes for this are described. ... Liu, K. C.Sim,and P. C. Woodland (2006). The CU-HTK Mandarinbroadcast news transcription system, Proc. -
EM_spd_D4Tech.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/Shin_TR626.pdf4 Aug 2009: Here, xi1 is the new estimate, xi the speed having the lowest correlation among three guesses. ... The secondcolumn shows the difference of the new estimate from the reference speed of 1540 m/s. -
A Generalised Derivative Kernel for Speaker Verification C. Longworth …
mi.eng.cam.ac.uk/~mjfg/cl336_INTER08.pdf2 Mar 2009: 5. ConclusionThis paper has introduced a new form of dynamic kernel thatcombines a static kernel applied over individual observationswith a generative model based approach to obtain a fixed di-mensional representation -
TRAINING AND ADAPTING MLP FEATURES FOR ARABIC SPEECH RECOGNITION
mi.eng.cam.ac.uk/research/projects/AGILE/publications/park_icassp09.pdf7 Oct 2009: Allthe schemes are evaluated in a common framework using an ArabicBroadcast News/Conversation transcription task. ... All thesetest sets consist of both Broadcast News and Broadcast Conversationstyles of data. -
3D ULTRASONIC STRAIN IMAGINGUSING FREEHAND SCANNING ANDA…
mi.eng.cam.ac.uk/reports/svr-ftp/housden_tr623.pdf28 Jan 2009: In IEEE UltrasonicsSymposium, 2007, pages 228–231, New York, USA, October 2007. ... In IEEE UltrasonicsSymposium, 2007, pages 355–358, New York, USA, October 2007. -
paper_pcw_v1.dvi
mi.eng.cam.ac.uk/research/projects/AGILE/publications/park_interspeech09.pdf7 Oct 2009: Once the MLP-based features have been derived for the en-tire training set, new HMM-based acoustic models must be es-timated. ... All testsets consist of Broad-cast News/Conversation style data. The LM was trained usingapproximately 1G words. -
paper.2col.dvi
mi.eng.cam.ac.uk/~mjfg/kai_ASP09.pdf2 Mar 2009: This paperdescribes a new framework for estimating transforms that arediscriminative in nature, but are less sensitive to this hypothesisissue. ... V. CONCLUSION. This paper has described a new framework for robustdiscriminative unsupervised adaptation. -
paramStudy_V_(TechR).dvi
mi.eng.cam.ac.uk/reports/svr-ftp/Shin_TR600.pdf4 Aug 2009: New York, 1993. 21. [2] P. Suetens, Fundamentals of Medical Imaging, Cambridge University Press, Cambridge, UK,. -
Model-Based Approaches to Speaker andEnvironment Adaptation Mark…
mi.eng.cam.ac.uk/~mjfg/mjfg_china09.pdf28 Apr 2009: Unsupervised Linear Transformation Estimation. • Estimation of all the transforms is based on EM:– requires the transcription/hypothesis of the adaptation data– iterative process using “current” transform to estimate new transform. -
IEEE TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING, VOL. ...
mi.eng.cam.ac.uk/~mjfg/cl336_ASP09.pdf2 Mar 2009: This can be used to motivate new kernels toapply to the SV task. ... By introducing new variablesb(s)k andξ(s)1k ,. , ξ. (s)N k for each. -
CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT NOISY CMLLR FOR…
mi.eng.cam.ac.uk/~mjfg/kim_tr611.pdf18 Feb 2009: In this work, a new approach for adaptive training on noise-corrupted trainingdata is presented. ... 5 Noisy CMLLR. Noisy CMLLR (NCMLLR) is a new form of linear transform. -
Learning to Track with Multiple Observers Björn StengerComputer…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2009-CVPR-hand-trackerpdf.pdf28 Jul 2009: At each frame a new weak classifier islearned and the ensemble is updated by replacing the leastreliable classifiers in each time step. ... A new framework wasproposed that evaluates the robustness and precision of ob-servers, allowing the user to choose -
doi:10.1016/j.patrec.2008.04.005
mi.eng.cam.ac.uk/~cipolla/archive/Publications/article/2008-PR-car-video-database.pdf28 Jul 2009: 1.2. Database description. We propose this new ground truth database to allow numericalevaluation of various recognition, detection, and segmentationtechniques. ... We re-usedthe color-index assignments from Shotton et al. (2006), and addedthe new -
Learning to Track with Multiple Observers Björn StengerComputer…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2009-CVPR-hand-trackingpdf.pdf28 Jul 2009: At each frame a new weak classifier islearned and the ensemble is updated by replacing the leastreliable classifiers in each time step. ... A new framework wasproposed that evaluates the robustness and precision of ob-servers, allowing the user to choose -
Uniform precision ultrasound strain imaging G.M. Treece, J.E. Lindop, …
mi.eng.cam.ac.uk/reports/svr-ftp/treece_tr624.pdf9 Mar 2009: Uniform precision ultrasound strain imaging. G.M. Treece, J.E. Lindop, A.H. Gee and R.W. PragerCUED/F-INFENG/TR 624. March 2009. Cambridge University Engineering DepartmentTrumpington StreetCambridge CB2 1PZ. England. Corresponding e-mail: -
doi:10.1016/j.patrec.2008.04.005
mi.eng.cam.ac.uk/~cipolla/publications/article/2008-PR-car-video-database.pdf28 Jul 2009: 1.2. Database description. We propose this new ground truth database to allow numericalevaluation of various recognition, detection, and segmentationtechniques. ... We re-usedthe color-index assignments from Shotton et al. (2006), and addedthe new -
Learning to Track with Multiple Observers Björn StengerComputer…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2009-CVPR-hand-trackerpdf.pdf28 Jul 2009: At each frame a new weak classifier islearned and the ensemble is updated by replacing the leastreliable classifiers in each time step. ... A new framework wasproposed that evaluates the robustness and precision of ob-servers, allowing the user to choose -
Learning to Track with Multiple Observers Björn StengerComputer…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2009-CVPR-hand-trackingpdf.pdf28 Jul 2009: At each frame a new weak classifier islearned and the ensemble is updated by replacing the leastreliable classifiers in each time step. ... A new framework wasproposed that evaluates the robustness and precision of ob-servers, allowing the user to choose
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.