Search
Search Funnelback University
51 -
100 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
-
4F12-notes-4.dvi
mi.eng.cam.ac.uk/~cipolla/lectures/4F12/Slides/4F12-notes-4.pdf2 Nov 2023: 12 p. ′13 p. ′14. p′21 p′22 p. ′23 p. ′24. ... vp24)p22. p′24. . . . . . Z. . . . -
EFFECTS OF THE USER MODEL ON SIMULATION-BASEDLEARNING OF DIALOGUE ...
mi.eng.cam.ac.uk/~sjy/papers/swsy05.pdf20 Feb 2018: The COMMUNICATOR systems in contrast onlyrequest between 24% and 43% of the unknown slots in each state. -
TWO-WAY CLUSTER VOTING TO IMPROVE SPEAKER DIARISATION PERFORMANCE S.…
mi.eng.cam.ac.uk/reports/svr-ftp/tranter_icassp05.pdf25 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 -
4F12-notes-1.dvi
mi.eng.cam.ac.uk/~cipolla/lectures/4F12/Slides/4F12-notes-1.pdf29 Sep 2023: CCD. • A typical digital SLR CCD measures about 24 16 mm. ... 24 Engineering Part IIB: 4F12 Computer Vision. Further reading. Students looking for a deeper understanding of computer vision might wish to con-sult the following publications, many of -
Applying Deep Learning in Non-native Spoken English Assessment
mi.eng.cam.ac.uk/~mjfg/ALTA/presentations/APSIPA2019_Knill.pdf21 Feb 2022: 1.0 indicates within one CEFR grade-level. 24/45. Assessment System Performance. • ... 1.0 indicates within one CEFR grade-level. 24/45. Performance Analysis. 25/45. -
Structured Discriminative Models Using Deep Neural-Network Features
mi.eng.cam.ac.uk/~mjfg/asru15-vanDalen.pdf11 Mar 2016: MPE— 7.15 11.06 14.37 24.54 16.79CML 6.95 11.00 14.29 24.39 16.68large-margin 7.02 10.92 14.16 24.28 ... Therefore the systems use graphemic lex-ica generated using an approach which is applicable to all Unicodecharacters [24]. -
Progress in English Conversational TelephoneSpeech Transcription Khe…
mi.eng.cam.ac.uk/research/projects/EARS/pubs/sim_sttmar05.pdf12 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. -
AUTOMATIC COMPLEXITY CONTROL FOR HLDA SYSTEMS X. Liu, M. ...
mi.eng.cam.ac.uk/reports/svr-ftp/liu_icassp2003.pdf19 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 -
INVESTIGATION OF ACOUSTIC MODELING TECHNIQUES FOR LVCSR SYSTEMS X. ...
mi.eng.cam.ac.uk/reports/svr-ftp/liu_icassp2005.pdf19 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. -
Reward Estimation for Dialogue Policy Optimisation Pei-Hao Su, Milica …
mi.eng.cam.ac.uk/~sjy/papers/sugy18.pdf20 Feb 2018: In this section, a Gaussianprocess-based reward estimator is described which uses active learning tolimit intrusive requests for feedback and a noise model to mitigate the effectsof inaccurate feedback [24]. ... 24. Figure 13: The number of times each -
A LANGUAGE SPACE REPRESENTATION FOR SPEECH RECOGNITION
mi.eng.cam.ac.uk/~mjfg/icassp15-ragni.pdf18 May 2015: There are many options to select the form of rep-resentation of the clusters and the combination method to employ[18, 17, 13, 24, 25]. ... 20, no. 6, pp. 1713–1724, 2012. [24] V. Diakoloukas and V. -
Context adaptive training with factorized decisiontrees for HMM-based …
mi.eng.cam.ac.uk/~sjy/papers/yzmy11.pdf20 Feb 2018: 24].3 Available at http://mi.eng.cam.ac.uk/˜farm2/emphasis.4 Cohen’s Kappa cannot be used here because the phrases are not distinct elements. ... Interspeech, 2010, pp. 410–413. [24] S. Young, G. Evermann, M. Gales, T. -
Still Talking to Machines (Cognitively Speaking) Steve Young…
mi.eng.cam.ac.uk/~sjy/papers/youn10a.pdf20 Feb 2018: partition ex-plicitly records the fact that x = a and the existing partitionis updated to record the fact that x = ā [24]. -
Part IA Computing CourseTutorial Guide to C++ Programming Roberto ...
mi.eng.cam.ac.uk/~cipolla/resource/tutorial.pdf12 Apr 2022: 24. // testing for real solutions to a quadraticd = bb - 4ac;if(d >= 0.0){. // -
main.dvi
mi.eng.cam.ac.uk/~sjy/papers/ywss05.pdf20 Feb 2018: At this point, the dialog state probabilities given by equation 24 are omputed. ... P1. find P2. (a) task 1.0. P1 b=1.0. b=0.7. b=0.3. b=0.24. -
PROC IEEE, VOL. 101, NO. 5, 1160-1179, 2013 1 ...
mi.eng.cam.ac.uk/~sjy/papers/ygtw13.pdf20 Feb 2018: A similar approach is takenin [24], except that both slot values and their complements areused to build a frame. ... R(θ) = 1N. Nn=1. Tn1t=0. θ log π(ânt |bnt ,θ)Q(bnt , ânt ) (24). -
Quantitative Evaluation of User Simulation Techniquesfor Spoken…
mi.eng.cam.ac.uk/~sjy/papers/scgy05.pdf20 Feb 2018: The Pietquin model. Train TestPrecision Recall Precision Recall. BIG 19.74 24.11 17.83 21.66LEV 43.11 35.07 37.98 31.57PTQ 45.00 36.35 40.16 -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/GMT_4YP_24_2Main > GMT_4YP_24_2. Dr Graham Treece, Department of Engineering. -
Roberto Cipolla - Professor of Information Engineering
mi.eng.cam.ac.uk/~cipolla/publications.htmImage and Vision Computing, 24(6):639-647, June 2006. O. Arandjelovic and R. -
narrow wheels (8) do ub le p ins ( ...
mi.eng.cam.ac.uk/IALego/trays.pdf1 Jan 2024: axle. s (. 80). bush pins (16). plates (46). 127 beams (24)o. -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/GMT_EqnSurfIn the Windows version this will be saved in uncompressed 24-bit. -
Index of /~cipolla/lectures/PartIB/old
mi.eng.cam.ac.uk/~cipolla/lectures/PartIB/old/KDTest.zip 24-May-2006 11:00 15K. -
Professor Steve Young, Publications
mi.eng.cam.ac.uk/~sjy/publications.htmlP-H. Su, M. Gasic and S. Young (2018). "Reward Estimation for Dialogue Policy Optimisation." Computer Speech and Language, 51(1):24-43. ... B. Thomson and S. Young (2010). "Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems." -
paper.dvi
mi.eng.cam.ac.uk/~mjfg/ragni_ASRU11.pdf20 Dec 2011: 24, pp. 648–662, 2010. [5] S.-X. Zhang, A. Ragni, and M. -
Roberto Cipolla - Professor of Information Engineering
mi.eng.cam.ac.uk/~cipolla/publications_all.htmImage and Vision Computing, 24(6):639-647, June 2006. O. Arandjelovic and R. -
MultiMedia Document Retrieval (1997-2000)
mi.eng.cam.ac.uk/research/projects/Multimedia_Document_Retrieval/7 Oct 2001: May 1998 - The TREC-7 Evaluation. The overall word error rate for our recognition system on the 100 hours of TREC-7 SDR data was 24.8%, the lowest in the -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/GMTPublicationsPattern Recognition Letters. Vol. 24, No. 4-5, pp. 705-713, 2003. G. ... Vol. 24, S1, pp. S293-S294, April 2016. T. Turmezei, K. Poole, G Treece. -
Improving Retrieval on Imperfect Speech Transcriptions
mi.eng.cam.ac.uk/reports/full_html/jourlin_sigir99.html/8 Mar 2000: HTK. ATT. Dragon. Base1. Sheff. Base2. DERA. WER. 24.8. 31.0. 29.8. -
References [1] Control-DAG: Constrained decoding for…
mi.eng.cam.ac.uk/~wjb31/PUBS/29 Apr 2024: 2024. To appear at NAACL’24. ... 24] Improving the quality trade-off for neural machine translation multi-domain adaptation. -
Woodland et al.: English CTS Systems 2003 CU-HTK English ...
mi.eng.cam.ac.uk/research/projects/EARS/pubs/woodland_rt03s.pdf24 Jul 2003: CNC P4.[123]P5.[123] 19.8 24.3 27.0 23.9%WER on eval02 for all stages of 2002 system, manual segmentation. • ... Final NCE is 0.318. Cambridge UniversityEngineering Department. Rich Transcription Workshop 2003 24. -
Index of /~cipolla/archive/Public-Understanding
mi.eng.cam.ac.uk/~cipolla/archive/Public-Understanding/2019-Metail.mp4 24-Apr-2019 11:11 453M. -
Abstract for johnson_trec7
mi.eng.cam.ac.uk/reports/abstracts/johnson_trec7.html27 Jul 2020: The broadcast news audio was transcribed using a 2-pass gender-dependent HTK speech recogniser which ran at 50 times real time and gave an overall word error rate of -
Royal Society Meeting on Geometry in Computer Vision
mi.eng.cam.ac.uk/~cipolla/royal_society.html28 Nov 2006: Session 3: Grouping and Matching. Thursday 24 July, 09.30-12.30 (Chair: Dr A. ... Session 4: Geometry and Statistics. Thursday 24 July, 14.00-17.40 (Chair: Dr R. -
Publications
mi.eng.cam.ac.uk/~gmt11/stradwin/publications.htmUltrasound in Medicine and Biology, Vol. 24, No. 6, pp. 855-869, July 1998. -
tr.dvi
mi.eng.cam.ac.uk/reports/svr-ftp/prager_tr436.pdf28 Jun 2002: Communicationsof the ACM, 24(6):381–395, June 1981. [4] Jr. J. M. Kofler and E. ... Ultrasound in Medicine and Biology,24(4):535–542, 1998. [7] J. J. More. The Levenberg-Marquardt algorithm: implementation and theory. -
The Cambridge University Spoken Document Retrieval System
mi.eng.cam.ac.uk/reports/full_html/johnson_icassp99.html/8 Mar 2000: Sheffield. 39.8. 37.6. 37.1. 34.6. HTK-1. 28.6. 24.9. 24.7. 22.2. HTK-2. ... 24.1. 21.5. 21.2. 18.7. Table 3: Story-based % Word Error Rates for TREC-6 data. -
ICASSP2014b.dvi
mi.eng.cam.ac.uk/~mjfg/yoshioka_ICASSP14.pdf3 Apr 2014: Workshop. Automat. SpeechRecognition, Understanding, 2011, pp. 24–29. [13] O. Abdel-Hamid and H. ... Mag.,vol. 29, no. 6, pp. 114–126, 2012. [24] T. Yoshioka, X. -
Abstract for clarkson_icassp97
mi.eng.cam.ac.uk/reports/abstracts/clarkson_icassp97.html27 Jul 2020: Both techniques yield a significant reduction in perplexity over the baseline trigram language model when faced with multi-domain test text, the mixture-based model giving a 24% reduction and the -
paper.dvi
mi.eng.cam.ac.uk/~mjfg/wang_is2012.pdf13 Jun 2013: RVTSJ 14.9 29.6 18.3 43.6 26.6RAT RVTSJ 13.7 28.5 15.0 42.2 24.9. -
Roberto Cipolla - Professor of Information Engineering
mi.eng.cam.ac.uk/~cipolla/publications_procs.htmProfessor Roberto Cipolla, Department of Engineering. Conference Proceedings. 2023.. G. Bae, M. de la Gorce, T. Baltrusaitis, C. Hewitt, D. Chen, J. Valentin, R. Cipolla and D. Chen. DigiFace-1M: 1 million digital face images for face recognition. -
CU-HTK March 2001 Hub5 system Phil Woodland, Thomas Hain, ...
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_lvcsr01.pdf31 May 2001: Cambridge UniversityEngineering Department. Hub5 Workshop 24. Woodland, Hain, Evermann & Povey: CU-HTK March 2001 Hub5 system. ... 5 29.2 24.6Rover vote 20.1 25.2 30.2 25.3Rover conf 19.9 24.6 29.8 24.9. -
Two-way Cluster Voting to Improve Speaker Diarisation Performance
mi.eng.cam.ac.uk/reports/full_html/tranter_icassp05.html/31 Mar 2005: full. 30.30. 19.94. 19.15. 32.06. 37.92. 10.74. 24.26. † St. diag. ... full. 24.31. 19.97. 12.75. 19.34. 22.77. 17.50. 19.09. † St. diag. -
The 1997 HTK Broadcast News Transcription System
mi.eng.cam.ac.uk/reports/full_html/woodland_darpa98.html/1 Mar 2000: 24.6. F5. 28.6. 23.8. 27.1. 24.8. FX. 58.5. 55.2. 56.8. 55.4. ... 25.3. 29.0. 24.3. 28.1. F2. 38.3. 41.6. 35.7. 37.3. F3. 25.3. -
Machine Intelligence Laboratory
mi.eng.cam.ac.uk/Main/AHGPublicationsUltrasound in Medicine and Biology, 24(6):841-854, July 1998. R. Rohling, A. ... Osteoarthritis and Cartilage, 24(S293-S294), April 2016. T.D. Turmezei, A.H. Gee, K.E.S. -
Covariance Modelling for Noise-Robust Speech Recognition R. C. van ...
mi.eng.cam.ac.uk/~mjfg/vandalen_INTER08.pdf16 Jun 2008: 20 I. 2. –24. yst1yst. yst1. 35 = Dyet (13). where D is the dynamic coefficient matrix and yet is the vectorof static coefficients in the appropriate window. -
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. ... 23.1. 24.3. 19.7 @ 2609. 5. 3. 16.7. 17.3. 24.3. 28.9. -
The 1998 HTK Broadcast News Transcription System: Development and…
mi.eng.cam.ac.uk/reports/full_html/woodland_darpa99.html/2 Mar 2000: F5. 24.4. 23.8. 21.4. 20.0. FX. 32.7. 32.7. 30.9. 30.9. Overall. ... 19.1. 17.2. 24.7. 30.9. P3. bg. 1/N. 19.1. 11.9. 20.4. 27.6. -
Spoken Document Retrieval for TREC-7 at Cambridge University
mi.eng.cam.ac.uk/reports/full_html/johnson_trec7.html/30 Mar 2000: This system gave a word error rate of 24.1% on the TREC-6 test data. ... map. stop. stem. CUHTK. 24.8. 25.0. 24.9. 22.8. 22.3. Dragon. 29.8. -
Effects of Out of Vocabulary Words in Spoken Document Retrieval
mi.eng.cam.ac.uk/reports/full_html/woodland_sigir00.html/14 Aug 2000: ID. BASE. BRF. UBRF. 3k. 22.2. 24.4. 33.3. 7k. 33.8. 37.5. -
General Query Expansion Techniques for Spoken Document Retrieval
mi.eng.cam.ac.uk/reports/full_html/jourlin_esca99.html/2 Mar 2000: Our retrieval system was run on 7 different sets of automatically transcribed broadcast news texts with a WER varying from 24.8% to 66.2%. ... The overall system gave a WER of 24.8% which corresponded to a Processed Term Error Rate [11] (which more
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
- news |u:www.enterprise.cam.ac.uk (23) · moments ago
- Economics lesson |u:www.trin.cam.ac.uk (430) · moments ago
- `WATSON Ruth Isabella` (1) · moments ago
- `studied economics at Cambridge` |u:www.jbs.cam.ac.uk (14) · moments ago
Recent searches
Your search history is empty.