Search
Search Funnelback University
- Refined by:
- Date: 2015
1 -
33 of
33
search results for TALK:PC53 20 |u:mi.eng.cam.ac.uk
where 0
match all words and 33
match some words.
Results that match 1 of 2 words
-
mi.eng.cam.ac.uk/research/dialogue/EPSRCProj/rss.xml
mi.eng.cam.ac.uk/research/dialogue/EPSRCProj/rss.xml22 Sep 2015: en Tue, 22 Sep 2015 07:38:20 GMT https://getnikola.com/ http://blogs.law.harvard.edu/tech/rss EPSRC Funded Research Project -
lect14
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect14.2up.pdf10 Nov 2015: 0.1 0.2 0.5 1 2 5 10 20 40. 0.1. 0.2. ... 0.5. 1. 2. 5. 10. 20. 40. False Alarm probability (in %). Miss. pro. babi. lity (i. n %. ). GMM SVM. MAP (τ)EER. -
lect2.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect2_pres.pdf10 Nov 2015: 20. -10. 0. 10. 20. -10. 0. 10. 0. 0.01. 0.02. ... 10. 010. 20. -10. 0. 10. 20. 0. 0.005. 0.01. P. -
lect1.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect1_pres.pdf10 Nov 2015: Bayes’ Rule is sometimes remembered as. posterior likelihood prior. 20 Engineering Part IIB: Module 4F10 Statistical Pattern Processing. ... 10. 20. 30. 40. 50. 60. 70. 80. 90. 100. False Positive. -
lect1.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect1.pdf10 Nov 2015: Bayes’ Rule is sometimes remembered as. posterior likelihood prior. 20 Engineering Part IIB: Module 4F10 Statistical Pattern Processing. ... 10. 20. 30. 40. 50. 60. 70. 80. 90. 100. False Positive. -
lect3_pres.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect3_pres.pdf10 Nov 2015: 0.05. 0.1. 0.15. 0.2. 0.25. 0.3. 0.35. 20. 4 Engineering Part IIB: Module 4F10 Statistical Pattern Processing. ... 4. 2. 0. 2. 4. 6. 83 ITERATIONS. 20 Engineering Part IIB: Module 4F10 Statistical Pattern Processing. -
lect3.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect3.pdf10 Nov 2015: 05. 1015. 2025. 0. 5. 10. 15. 20. 250. 0.05. 0.1. -
Joint Decoding of Tandem and Hybrid Systems for Improved ...
mi.eng.cam.ac.uk/~ar527/wang_is2015a.pdf3 Jun 2015: 20, no. 1, pp. 14–22, 2012. [17] G. Hinton, L. Deng, D. ... 34, no. 1, pp. 25–40, 2001. [20] H. Misra, H. Bourlard, and V. -
lect5.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect5.pdf10 Nov 2015: 1. 1. x1. 1x2. 0.5NOR. (d) NOR operator. 20 Engineering Part IIB: Module 4F10 Statistical Pattern Processing. -
A LANGUAGE SPACE REPRESENTATION FOR SPEECH RECOGNITION
mi.eng.cam.ac.uk/~mjfg/icassp15-ragni.pdf18 May 2015: Though for speaker adaptation this may be reason-able [20], for language adaptation this is expected to be suboptimalas different eigen-languages may have different acoustic realisationsof context-dependencies. ... Rep. CUED/F-INFENG/TR263,Cambridge -
lect12.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect12_pres.pdf25 Nov 2015: Classifier 1. Processing. 20. 4F10: Statistical Pattern Processing. Adaptive Directed Acyclic Graph. -
A LANGUAGE SPACE REPRESENTATION FOR SPEECH RECOGNITION A. Ragni, ...
mi.eng.cam.ac.uk/~ar527/ragni_icassp2015a.pdf6 Apr 2015: Though for speaker adaptation this may be reason-able [20], for language adaptation this is expected to be suboptimalas different eigen-languages may have different acoustic realisationsof context-dependencies. ... Rep. CUED/F-INFENG/TR263,Cambridge -
UNICODE-BASED GRAPHEMIC SYSTEMS FOR LIMITED RESOURCE LANGUAGES M.J.F. …
mi.eng.cam.ac.uk/~ar527/gales_icassp2015a.pdf21 Jan 2015: This was the approach adopted from the graphemicModern Standard Arabic (MSA) systems in [19] and the system forthe RATS data in [20]. ... 26, no. 4, pp. 229–243, 2012. [20] Mark J. F. Gales and Federico Flego, “Model-based ap-proaches for degraded -
Improving Speech Recognition and Keyword Searchfor Low Resource…
mi.eng.cam.ac.uk/~ar527/mendels_is2015a.pdf3 Jun 2015: The training data for the other languageswas retrieved from the Leipzig corpora [20]. ... 485–525. [19] B. Carpenter. Lingpipe dynamiclmclassifier. [Online]. Avail-able: http://alias-i.com/lingpipe/docs/api/com/aliasi/classify/DynamicLMClassifier.html. -
lect5.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect5_pres.pdf10 Nov 2015: 1. 1. 1. 1. 1.5 AND. 25. 20 Engineering Part IIB: Module 4F10 Statistical Pattern Processing. -
Joint Decoding of Tandem and Hybrid Systems for Improved ...
mi.eng.cam.ac.uk/~mjfg/interspeech15-wang-babel.pdf9 Oct 2015: Joint decoding can be viewed as a single multi-stream sys-tem [20, 21]. ... 20, no. 1, pp. 14–22, 2012. [18] G. Hinton, L. Deng, D. -
Association Between Femur Size and a FocalDefect of the ...
mi.eng.cam.ac.uk/reports/svr-ftp/gee_tr696.pdf3 Feb 2015: 5. 330. mean surface density (mg/cm )20 660. (a) Male mean CMSDp (vertex)p (cluster)% change per s.d. ... exploration 1 Hgt Age Wgt Shp Site Hgt 2.20 102 40 3.50n=308 1 S0 Age Wgt Shp Site S0 5.09 107 208 7.84males 1 S0 Age -
Unicode-based Graphemic Systems for Limited Resource Languages
mi.eng.cam.ac.uk/~mjfg/icassp15-gales-babel.pdf18 May 2015: 20]. This expert derived set of decision tree ques-tions was compared with the unicode-based graphemic approach de-scribed in this paper. ... 26, no. 4, pp. 229–243, 2012. [20] M.J.F. Gales and F. -
Annotating large lattices with the exact word error Rogier ...
mi.eng.cam.ac.uk/~mjfg/Kernel/van_dalen-2015-exact_error.pdf16 Jun 2015: Theimplementation of the incremental algorithm uses the author’sFlipsta C++ library for finite-state automata [20], open-sourcedunder the permissive Apache License [21], which allows morelazy operations. ... 101. 102. 103. Mem. ory. use. (MB. ). 0 10 -
Improving Speech Recognition and Keyword Searchfor Low Resource…
mi.eng.cam.ac.uk/~mjfg/interspeech15-mendels-babel.pdf9 Oct 2015: The training data for the other languageswas retrieved from the Leipzig corpora [20]. ... 485–525. [19] B. Carpenter. Lingpipe dynamiclmclassifier. [Online]. Avail-able: http://alias-i.com/lingpipe/docs/api/com/aliasi/classify/DynamicLMClassifier.html. -
lect4.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect4.pdf10 Nov 2015: 0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 20.8. ... 20 Engineering Part IIB: Module 4F10 Statistical Pattern Processing. Variational Approaches. -
lect8.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect8_pres.pdf20 Nov 2015: x =. [. x1x2. ]. Φ(x) =. 12x12x22x1x2x21x22. 32. 20 Engineering Part IIB: 4F10 Statistical Pattern Processing. -
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. -
lect9_pres
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect9_pres.2up.pdf10 Nov 2015: 20 Engineering Part IIB: 4F10 Statistical Pattern Processing. Determining the Bias. -
lect4.dvi
mi.eng.cam.ac.uk/~mjfg/local/4F10/lect4_pres.pdf10 Nov 2015: 0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 20.3. ... 4F10: Statistical Pattern Processing. EM Example. 0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 20.3. -
IMPROVING MULTIPLE-CROWD-SOURCED TRANSCRIPTIONS USING A…
mi.eng.cam.ac.uk/~mjfg/ALTA/publications/van_dalen-2015-improving.pdf11 Feb 2015: The speech recogniser with an unbiased language model obtainsa word error rate of 40.4 %. 1http://www.wiki.cl.cam.ac.uk/rowiki/NaturalLanguage/ALTA. 20. 25. 30. 35. Wor. der. ... Constrained ASR. Longest. Oracle. (a) Picking one whole transcription. 20. -
main
mi.eng.cam.ac.uk/~cipolla/publications/article/2016-CVIU-EVTTS.pdf10 Sep 2015: 20. [37] A. Klin, W. Jones, R. Schultz, F. Volkmar, The enactive mind, or from actions to563cognition: lessons from autism, Philos. ... Audio Speech Lang. Process. 20 (5).591. [47] J. Latorre, V. Wan, M. -
main
mi.eng.cam.ac.uk/~cipolla/archive/Publications/article/2016-CVIU-EVTTS.pdf10 Sep 2015: 20. [37] A. Klin, W. Jones, R. Schultz, F. Volkmar, The enactive mind, or from actions to563cognition: lessons from autism, Philos. ... Audio Speech Lang. Process. 20 (5).591. [47] J. Latorre, V. Wan, M. -
Department of Engineering 1 Monoids: e�cient segmental features…
mi.eng.cam.ac.uk/~mjfg/Kernel/van_dalen-2013-tr-monoid_features17 Apr 2015: is function is applied separately to each feature in (20). 4.1 Instance: likelihood score-spaces. ... f(o2) =. 0.4 0.1 00 0.2 0.20 0 0. . (22a)e way to read this matrix is. -
Department of Engineering 1 Generative Kernels and Score-Spaces…
mi.eng.cam.ac.uk/~mjfg/Kernel/rcv25_2015_y3.pdf1 Jun 2015: 194 Bayesian log-linear models. 20. 4.1 Bayesian models. 204.2 Bayesian conditional models. ... f(o2) =. 0.4 0.1 00 0.2 0.20 0 0. . (24a)e way to read this matrix is. -
Model-based Approaches to Robust SpeechRecognition in Diverse…
mi.eng.cam.ac.uk/~mjfg/thesis_yw293.pdf27 Oct 2015: words in the Resource Management (RM) task (1988-1992)[195] to 20,000 words in the Wall. -
"Refinements in Hierarchical Phrase-Based Translation…
mi.eng.cam.ac.uk/~wjb31/ppubs/jpino2015HieroRefinementsThesis.pdf6 Feb 2015: CHAPTER 2. STATISTICAL MACHINE TRANSLATION 20. Och et al. (1999) notice that using an erroneous version of the source-channel model, that is using the following equation:. -
PROBABILISTIC ACOUSTIC MODELLING FOR PARAMETRIC SPEECH SYNTHESIS Sean …
mi.eng.cam.ac.uk/~wjb31/ppubs/shannon2014probabilistic-thesis.pdf2 Feb 2015: 2.20). where f̃ is a K-dimensional vector. The functions F and len are sufficient statistics for.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.