Search
Search Funnelback University
51 -
100 of
446
search results for TALK:PC53 20 |u:mi.eng.cam.ac.uk
where 0
match all words and 446
match some words.
Results that match 1 of 2 words
-
Sparse and Semi-supervised Visual Mapping with the S3GP Oliver ...
mi.eng.cam.ac.uk/reports/svr-ftp/williams_cvpr06.pdf3 Apr 2006: 2.1. Gaussian process regression. Gaussian process learning defines a probability distrib-ution directly onto the space of functions [20]. ... Nature, 418:838, 2002. [20] C. Williams and C. Rasmussen. Gaussian processes for re-gression. -
FACTOR ANALYSED HIDDEN MARKOV MODELS A-V.I. Rosti and M.J.F. ...
mi.eng.cam.ac.uk/reports/svr-ftp/rosti_icassp2002.pdf26 Jan 2004: 19). Σ̂(o). jm =1. PT. t=1 γ(o)jm(t). TX. t=1. γ(o)jm(t)diag. “. oto′. t (20). h. Ĉj µ̂(o)jm. i h. -
��������� ��� ��������������� ������� ��…
mi.eng.cam.ac.uk/reports/svr-ftp/jourlin_sigir99.pdf8 Mar 2000: ÂJÙYÉÀÃEùZ@-MÐZÃ;ÄÂcÏcÃ79ÄzÃ Ø À¿ÅÀÌZÆÌZÆÇzkÃ3Þß.à.Ý%î#ïEÞWÇzà ¿TÇ3Ø ÌcÉÀÉ=Ã;Ø;ÇzÀÌZÆNÚoÊÇzÍà ÂcÆNÆÈkÍ«Ù/Ã;Ä7ÌcËÒÈYÃ;ÄÅÓÇzÃÑÄzÍ¿=ÆNÁ|ÂJÄzÃ;ÆÇzkà ¿ÅÀ¿. 0 10 20 30 -
Predicting hip fracture type with cortical bone mapping (CBM)in ...
mi.eng.cam.ac.uk/reports/svr-ftp/treece_tr695.pdf26 Jan 2015: Predictive value of BMD for hip and other fractures. Journal of Bone and Mineral Research 20 (7),1185–1194. ... Medical Image Analysis 20, 249–264. Treece, G. M., Gee, A. H., Mayhew, P. -
SPOKEN DOCUMENT RETRIEVAL FOR TREC-8 AT CAMBRIDGE UNIVERSITY S.E. ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_trec8.pdf10 Apr 2000: Rec. HTK cc-proc HTK-p1 LIMSI NIST-B2Error 55.51 37.93 67.86 57.20 62.46Rec. ... 6Another method of modifying the TER to model retrieval weighting moreclosely can be found in [20]. -
Automatic Cast Listing in Feature-Length Films with Anisotropic…
mi.eng.cam.ac.uk/reports/svr-ftp/arandjelovic_CVPR06.pdf21 Mar 2006: We quan-tify this using what we call theweighted Description LengthDLw and merge tentative classes ifDLw < threshold(we usedthreshold = 20). ... 4. [20] G. Jaffŕe and P. Joly. Improvement of a person labelling methodusing extracted knowledge on -
An Illumination Invariant Face Recognition System forAccess Control…
mi.eng.cam.ac.uk/reports/svr-ftp/oa214_BMVC_2004_paper1.pdf8 Aug 2005: 10. 15. 20. 25. 30 05. 1015. 2025. 30. 0.92. 0.94. ... 0.96. 0.98. 1. 1.02. 1.04. 0. 5. 10. 15. 20. 25. -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/GMT_4YP_20_2Main > GMT_4YP_20_2. Dr Graham Treece, Department of Engineering. -
The sizzling steam engine
mi.eng.cam.ac.uk/IALego/steam.html1 Jan 2024: As well as turning the corner, the bevel gears also gear up in the ratio 20:12, so the governor spins faster than the flywheel. -
UK Speech Conference 2017 Programme
mi.eng.cam.ac.uk/UKSpeech2017/programme.html23 Dec 2017: Christine Evers, Imperial College. 14:50-15:20. CUED - LT1. ... 15:20-15:35. CUED - LR3A. Break (tea and coffee). 15:35-16:50. CUED - LR3. -
The prodigious pendulum clock
mi.eng.cam.ac.uk/IALego/clock.html1 Jan 2024: Starting from the black, 36-tooth bevel gear at the back left, there is a 20:24 reduction followed by a 12:24 reduction to the minute hand, which therefore rotates -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/GMT_VolMorphDefault is 20. -p {points}. sampling points. {points} sets the minimum number of points, in any direction, used to sample the initial and final files. ... The default is 20. -r {resolution}. triangulation resolution. {resolution} defines the resolution -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/GMT_IsoSurfMain > GMT_IsoSurf. Dr Graham Treece, Department of Engineering. IsoSurf. Note that the functionality in this software is now available (and in many ways improved) in Stradview, which is much more powerful and has a much nicer interface. The only -
Abstract for johnson_trec8
mi.eng.cam.ac.uk/reports/abstracts/johnson_trec8.html27 Jul 2020: The system gave an overall word error rate of 20.5% on the 10 hour scored subset of the corpus, the lowest in the track. -
Abstract for johnson_trec9
mi.eng.cam.ac.uk/reports/abstracts/johnson_trec9.html27 Jul 2020: The CU-HTK transcriptions from TREC-8 with Word Error Rate (WER) of 20.5% were used in conjunction with stopping, Porter stemming, Okapi-style weighting and query expansion using a -
Abstract for treece_tr665
mi.eng.cam.ac.uk/reports/abstracts/biomed/treece_tr665.html27 Jul 2020: Cortical thickness errors are confined to regions of thin cortex and are bounded by the extent to which the local density deviates from the peak, averaging 20% for 0.5 mm ... cortex. [3.6 MBytes PDF, 20 pages]. (ftp:) treece_tr665.pdf (http:) treece_tr665 -
Abstract for gales_tr284
mi.eng.cam.ac.uk/reports/abstracts/gales_tr284.html27 Jul 2020: On this task, the use of state information reduced the percentage of Gaussians computed to 10-15%, compared with 20-30% for the standard GS scheme, with little degradation in performance. -
Abstract for kykwong_ivc02
mi.eng.cam.ac.uk/reports/abstracts/kykwong_ivc02.html27 Jul 2020: Abstract for kykwong_ivc02. Image and Vision Computing vol 20 num 5-6 pp 441-448. -
Abstract for kershaw_nips95
mi.eng.cam.ac.uk/reports/abstracts/kershaw_nips95.html27 Jul 2020: Experiments show an average reduction in word error rate of 16% and 13% from the CI system on ARPA 5,000 word and SQALE 20,000 word tasks respectively. -
Abstract for james_icassp94
mi.eng.cam.ac.uk/reports/abstracts/james_icassp94.html27 Jul 2020: The paper presents the details of the algorithms used and compares performance with a number of conventional approaches using a 20 keyword vocabulary on the DARPA Resource Management Task. -
Abstract for gee_tr004
mi.eng.cam.ac.uk/reports/abstracts/biomed/gee_tr004.html27 Jul 2020: 2.5 MBytes PDF, 20 pages]. (ftp:) gee_tr004.pdf (http:) gee_tr004.pdf. -
Abstract for gee_tr392
mi.eng.cam.ac.uk/reports/abstracts/biomed/gee_tr392.html27 Jul 2020: 2.9 MBytes compressed PostScript, 20 pages]. (ftp:) gee_tr392.ps.gz (http:) gee_tr392.ps.gz. -
Abstract for hain_icassp99
mi.eng.cam.ac.uk/reports/abstracts/speech/hain_icassp99.html27 Jul 2020: The word error rate obtained is almost 20% better than our 1997 system on the development set. | -
Abstract for treece_tr577
mi.eng.cam.ac.uk/reports/abstracts/biomed/treece_tr577.html27 Jul 2020: Acquisition is complete within 2 seconds, and only an additional 20 seconds are required for generation of a full 3D strain volume. -
Abstract for treece_tr705
mi.eng.cam.ac.uk/reports/abstracts/biomed/treece_tr705.html27 Jul 2020: 10.6 MBytes pdf, 20 pages]. A derivative of this work has been submitted to the IEEE for possible publication. -
Abstract for witt_thesis
mi.eng.cam.ac.uk/reports/abstracts/witt_thesis.html27 Jul 2020: baseline and by up to 20% in comparison with standard adaptation methods. -
The Cambridge University Multimedia Document Retrieval Demo System
mi.eng.cam.ac.uk/reports/full_html/tuerk_sigir00demo.html/14 Aug 2000: On the Internet audio used here the run-time is increased due to reduced audio quality but the general level of transcription accuracy remains high at approximately 20% word error rate -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/GMTPublicationsMedical Image Analysis, Vol. 20, No. 1, pp. 249-264, January 2015. ... Proceedings of Medical Image Understanding and Analysis, pp. 17-20, Oxford, July 1999. -
Clinically Practical Freehand Three-Dimensional Ultrasound
mi.eng.cam.ac.uk/research/projects/cp3dus/22 Jul 2010: We have developed novel reconstruction algorithms to relax this constraint [1, 2, 15, 20, 23, 31, 33]. ... 20] R.J. Housden, A.H. Gee, R.W. Prager and G.M. Treece. Sensorless freehand 3D ultrasound for non-monotonic and intersecting frames. -
MultiMedia Document Retrieval (1997-2000)
mi.eng.cam.ac.uk/research/projects/Multimedia_Document_Retrieval/7 Oct 2001: The final WER on the 10 hour scored subset of the TREC-8 SDR corpus was 20.6% (the lowest in the evaluation). -
Segment Generation and Clustering in the HTK Broadcast News…
mi.eng.cam.ac.uk/reports/full_html/hain_darpa98.html/1 Mar 2000: On the BNeval97 only 0.18% of speech frames were lost, which is equivalent to 20.18 seconds. ... S. 0.56. 98.24. 1.20. T. 0.00. 1.19. 98.81. a). M. S. -
Two-way Cluster Voting to Improve Speaker Diarisation Performance
mi.eng.cam.ac.uk/reports/full_html/tranter_icassp05.html/31 Mar 2005: 20.78. 19.15. 32.06. 37.18. 10.74. 24.52. † St. 128mix. 27.66. 20.78. ... 19.86. 11.78. 20.37. 22.77. 12.28. 18.10. † St. 128mix. 26.34. 18.21. -
The 1998 HTK Broadcast News Transcription System: Development and…
mi.eng.cam.ac.uk/reports/full_html/woodland_darpa99.html/2 Mar 2000: 20.0%. 19.3%. F2. 16.1%. 3.4%. F3. 5.1%. 4.3%. F4. 4.9%. 28.2%. ... F3. F4. F5. FX. P1. tg. N/N. 19.9. 10.9. 20.5. 29.6. -
16/3/2014 NXT Race Car…
mi.eng.cam.ac.uk/IALego/trailer_files/trailer_steering.pdf1 Jan 2024: http://nxtprograms.com/NXT2/race_car/steps.html 20/43. 16/3/2014 NXT Race Car. http://nxtprograms.com/NXT2/race_car/steps.html 21/43. 12. 16/3/2014 NXT -
Effects of Out of Vocabulary Words in Spoken Document Retrieval
mi.eng.cam.ac.uk/reports/full_html/woodland_sigir00.html/14 Aug 2000: The results from adding 6 new terms to each query from the 20 top documents with UBRF is given in Table 3 which shows that this is a very effective strategy. -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/AHGPublicationsMedical Image Analysis, 20(1):249-264, February 2015. K.E.S. Poole, G.M. Treece, A.H. ... In Proceedings of Medical Image Understanding and Analysis, pages 17-20, Oxford, UK, 1999. -
A Method for Direct Audio Search with Applications to Indexing and…
mi.eng.cam.ac.uk/reports/full_html/johnson_icassp00.html/16 Jun 2000: However the transcription systems used (see e.g. [6]) typically run rather slower than real-time and have a word error rate of over 20%. ... 967. 5480s=61.0%. 114s=0.5%. window, 20@4s. 284. 4598s=51.2%. 122s=0.5%. Automatic segs. 38. -
The CUHTK-Entropic 10xRT Broadcast News Transcription System
mi.eng.cam.ac.uk/reports/full_html/odell_darpa99.html/1 Mar 2000: The Intel C compiler (version 2.4) seemed particularly efficient with the decoder running almost 20% faster than when compiled with gcc v2.7.2. ... These were trained in the same way as the first pass models but consisted of 13428 distinct models sharing -
The 1997 HTK Broadcast News Transcription System
mi.eng.cam.ac.uk/reports/full_html/woodland_darpa98.html/1 Mar 2000: 30.5%. 20.0%. F2. 16.2%. 16.1%. F3. 6.2%. 5.1%. F4. 14.1%. 4.9%. ... F1. 21.6. 20.8. F2. 35.6. 34.9. F3. 34.1. 32.4. F4. 26.2. -
Experiments in Broadcast News Transcription
mi.eng.cam.ac.uk/reports/full_html/woodland_icassp98.html/1 Mar 2000: We have found that using the full system with adaptation results in a 20% decrease in word error rate on broadcast news. ... 22.0. 21.2. F2. 18.8. 22.2. F3. 19.5. 20.5. F4. 27.3. 32.7. -
Class-based language model adaptation using mixtures of word-class…
mi.eng.cam.ac.uk/reports/full_html/moore_icslp00.html/2 Nov 2000: 149.36. 1003. 50. -. 218.47. 195.72. 217.10. 192.20. 1003. 50. 158.53. ... 215.31. 261.73. 209.20. 503. 250. 158.00. 148.52. 157.44. 146.53. 1003. 250. -. -
The Development of the Cambridge University RT-04 Diarisation System
mi.eng.cam.ac.uk/reports/full_html/tranter_rt04.html/10 Jan 2005: 22.4. 20.2. PLP. Y. -. Y. 25.4. 19.3. 27.9. 24.1. 24.3. ... 16.9. 17.8. 24.6. 24.0. 20.9 @ 2521. 10. 10. 19.9. 21.3. -
TEMPLATE DESIGN © 2008www.PosterPresentations.com Phase Processing…
mi.eng.cam.ac.uk/UKSpeech2017/posters/e_loweimi.pdf17 Nov 2017: 20. 30. 40. 50. 60. 70. 80. WE. R (. %). MFCCgMFCCBMFGDVTProposed. Robust Source-Filter Separation of Speech Signal in the Phase Domain. ... 0.40.30.20.10.00.10.20.30.40.5. τ VT. arg. [XMinPh]. arg. [XVT]. τ VT. Slide 1. -
Audio Indexing and Retrieval of Complete Broadcast News Shows
mi.eng.cam.ac.uk/reports/full_html/johnson_riao00.html/19 Apr 2000: This transcription, denoted. HTK-p2. , gave a WER of 20.5% on the scored subset. ... Post. RS. NRS. NS. #Dup. # windows. 0.1. B. 96.5. 44.20. -
Spoken Document Retrieval for TREC-9 at Cambridge University
mi.eng.cam.ac.uk/reports/full_html/johnson_trec9.html/23 Feb 2002: 20.5% on the 10-hour scoring subset of the TREC-8 data. ... 15. -. -. 38.68. 42.42. 37.27. 41.01. 100. 15. 8. 20. -
General Query Expansion Techniques for Spoken Document Retrieval
mi.eng.cam.ac.uk/reports/full_html/jourlin_esca99.html/2 Mar 2000: 54.40. 60.00. 54.20. 63.48. 8 = 5 - GP. 54.95. 59.13. -
The Cambridge University March 2005 Speaker Diarisation System
mi.eng.cam.ac.uk/reports/full_html/sinha_eurospeech05.html/22 Sep 2005: B D. models were formed by performing a single iteration of (mean-only) MAP adaptation, with τ =20 from the. ... IAC. DataSet. MS/FA/SPE/DER. Cluster Imp. Seg Imp. Base. Dev24. 1.2/1.1/17.9/20.17. 6.59@718. -
THE CU-HTK MARCH 2000 HUB5E TRANSCRIPTION SYSTEM
mi.eng.cam.ac.uk/reports/full_html/hain_stw00.html/12 Oct 2000: Decision tree state clustering [20] was used to select a set of context-dependent equivalence classes. ... P4b. 21.9. 33.7. 27.8. 0.287. P5a. 20.3. 32.7. 26.6. P5b. 21.0. -
Experimental Studies on Teacher-student Training of Deep Neural…
mi.eng.cam.ac.uk/UKSpeech2017/posters/q_li.pdf20 Nov 2017: PER (%)7-layer (500) 24.55 23.55RNN 23.84 20.59Ensemble 23.73 20.34. Table 1: RNN and ensemble teacher models with a 3-layer (500)fully-connected student -
Spoken Document Retrieval for TREC-8 at Cambridge University
mi.eng.cam.ac.uk/reports/full_html/johnson_trec8.html/30 Mar 2000: 2.9. 20.5. LIMSI. 82.0. 14.6. 3.4. 3.5. 21.5. CUHTK-p1. 77.3. 18.5. ... 12.4. 18.0. 83.07. 52.32. 48.93. ----. CUHTK-s1. 20.5. 27.8. 45.89. 55.29.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.