Search
Search Funnelback University
231 -
250 of
1,505
search results for news |u:mi.eng.cam.ac.uk
Fully-matching results
-
Online publications for Dr Tony Robinson
mi.eng.cam.ac.uk/reports/people/ajr.html27 Jul 2020: Contact:Title THE APPLICABILITY OF LANGUAGE MODEL ADAPTATION FOR THE BROADCAST NEWS TASK. ... Contact:Title A NEW FREQUENCY SHIFT FUNCTION FOR REDUCING INTER-SPEAKER VARIANCE. Abstract: tuerk_eurospeech93b. -
Abstract for johnson_icassp00
mi.eng.cam.ac.uk/reports/abstracts/johnson_icassp00.html27 Jul 2020: Results on data from ABC news broadcasts show that the method can successfully locate matches several hundred times faster than real-time and requires less than a second of cue-audio. ... By applying the match recursively to the data, repeated sections -
Model-based Segmentation
mi.eng.cam.ac.uk/~gmt11/stradwin/fit_model.htmcontours". This generates a new set of contours for this object. You can choose whether to insert contours onto every frame or every n frames, counting from the current frame. -
Unsupervised Language Model Adaptation for Mandarin…
mi.eng.cam.ac.uk/reports/svr-ftp/mrva_icslp06.pdf20 Jan 2007: Abstract. This paper investigates unsupervised language model adaptationon a new task of Mandarin broadcast conversation transcription. ... The systemthen performed the P3 stage using these new fourgram lattices withadapted LM scores. -
wxDicom
mi.eng.cam.ac.uk/~gmt11/wxDicom/image.htmlLocal mask (Bitonic X). Use new locally-varying morphology, which automatically chooses the appropriate mask, of any form, from the local properties of the data. -
Abstract for hain_darpa98
mi.eng.cam.ac.uk/reports/abstracts/hain_darpa98.html27 Jul 2020: Abstract for hain_darpa98. Proc. 1998 DARPA Broadcast News Transcription and Understanding Workshop. ... April 1998. This paper describes the segmentation, gender detection and segment clustering scheme used in the 1997 HTK broadcast news evaluation -
Abstract for gales_tr284
mi.eng.cam.ac.uk/reports/abstracts/gales_tr284.html27 Jul 2020: All the new schemes make use of state information, specifically which state each of the components belongs to. ... These new approach are compared with the standard GS scheme on a large vocabulary speech recognition task. -
Abstract for hain_icslp98
mi.eng.cam.ac.uk/reports/abstracts/hain_icslp98.html27 Jul 2020: Abstract for hain_icslp98. Proc. ICSLP'98, Sydney. SEGMENTATION AND CLASSIFICATION OF BROADCAST NEWS AUDIO. ... The segmentation system has been evaluated on the DARPA 1997 broadcast news data set and detailed segmentation accuracy results are presented. -
Abstract for james_thesis
mi.eng.cam.ac.uk/reports/abstracts/james_thesis.html27 Jul 2020: Consequently, new methods are required to allow users to pin-point specific items of interest in large data collections. ... In a baseline system, a new technique for wordspotting allows items matching an arbitrary expression of the information -
nips7.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/williams_nips2004.pdf9 Aug 2005: contaminated set and for the new contamination-tolerant VIC outlined in this paper. ... 14] A.K. Jain. Fundamentals of Digital Image Processing. System Sciences. Prentice-Hall, New Jersey, 1989. -
ADAPTATION OF PRECISION MATRIX MODELS ON LARGE VOCABULARYCONTINUOUS…
mi.eng.cam.ac.uk/reports/svr-ftp/sim_icassp2005.pdf12 Apr 2005: Experimentalresults are presented based on the MPE trained Subspace for Pre-cision and Mean models, evaluated on both broadcast news andconversational telephone speech English tasks. ... Experimental results are presented based on two LVCSR Englishtasks: -
Abstract for tham_ml94
mi.eng.cam.ac.uk/reports/abstracts/tham_ml94.html27 Jul 2020: Abstract for tham_ml94. To appear in: Machine Learning: Proceedings of the Eleventh International Conference (ML'94), New Brunswick, New Jersey, USA. -
MVA '96 IAPR Workshop on Machine Vision Applications. November.…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/1996-MVA-weld.pdf13 Mar 2018: 3. Perturb the camera position to a new position, ensuring that the contour is continually tracked and centered in the image field. ... Due t o the approximations made in this algorithm, the motion vector is not exact, but it does ensure that the new -
A Practical Method for Estimation of PointLight-Sour ces Martin ...
mi.eng.cam.ac.uk/reports/svr-ftp/weber_bmvc2001.pdf29 Nov 2003: Isard. ActiveContours. Springer, New York, 1998. [2] R. Cipolla andP. Giblin. ... 12] R.J.Woodham.Gradientandcurvaturefrom thephotometric-stereomethod,includ-ing local confidenceestimation.JOSA, 11:3050–3068,1994. [13] P.L. WorthingtonandE.R. -
CU-HTK March 2001 Hub5 system Phil Woodland, Thomas Hain, ...
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_lvcsr01.pdf31 May 2001: Stages similar to last year. • New MMIE models. • Normalisation after resegmentation based onP1 output. ... Lattice generation & rescoring. • MLLR and MAP adaptation. • New version supports PLP, VTLN as used in eval. • -
Abstract for tranter_tr464
mi.eng.cam.ac.uk/reports/abstracts/tranter_tr464.html27 Jul 2020: news (BN) and conversational telephone speech (CTS) domains. -
Investigation of multilingual speech-to-text systems for use in…
mi.eng.cam.ac.uk/~kmk/presentations/UEdin_Feb14_Knill.pdf12 May 2016: Multilingual STT for Spoken Term Detection. IARPA Babel Program. • Goal - rapidly develop spoken term detection in new languages. – ... Reduce overhead in deploying new language? • Language Independent Acoustic Models. – -
The Cambridge University March 2005 Speaker Diarisation System R. ...
mi.eng.cam.ac.uk/reports/svr-ftp/sinha_eurospeech05.pdf23 Jun 2005: These new models are then used toresegment the data using a Viterbi decode. ... C. Woodland, “Recent Advances inBroadcast News Transcription,” in Proc. ASRU, Decem-ber 2003, pp. -
Abstract for logan_sst96
mi.eng.cam.ac.uk/reports/abstracts/logan_sst96.html27 Jul 2020: B. T. Logan and A. J. Robinson. Dec 1996. This paper describes a new algorithm to enhance and recognise noisy speech when only the noisy signal is available. ... These likelihoods are used to weight each observation to form a new estimate of the noise -
Abstract for dick_eccv00
mi.eng.cam.ac.uk/reports/abstracts/dick_eccv00.html27 Jul 2020: In order to extract this 3D model the scene is represented as a collection of layers and a new method for layer extraction is described. ... The new segmentation method differs from previous methods in that it uses a specific prior model for layer shape.
Refine your results
Date
- 555 2018
- 199 2020
- 97 2005
- 61 2014
- 59 2006
- 58 Uncertain
- 58 2000
- 41 2008
- 39 2004
- 35 2003
- 33 2022
- 31 2007
- 30 2015
- 28 Past year
- 28 2023
- 23 2009
- 20 2017
- 19 2010
- 18 2024
- 18 2021
- 17 2019
- 16 2013
- 15 Past 6 months
- 14 2016
- 14 Past 3 months
- 11 Past month
- 9 2001
- 8 2012
- 7 2002
- 6 2011
- 6 1999
- 2 Past week
- 2 Past fortnight
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.