Search

Search Funnelback University

Search powered by Funnelback
10 results 20 results 50 results
Relevance Date (Newest first) Date (Oldest first) Title (A-Z) Title (Z-A) Distance URL (A-Z) URL (Z-A) Shuffle
1 - 10 of 14 search results for TALK:PC53 20 |u:mi.eng.cam.ac.uk where 0 match all words and 14 match some words.

  1. Results that match 1 of 2 words

  2. SYSTEM COMBINATION AND SCORE NORMALIZATION FOR SPOKEN TERM DETECTION

    mi.eng.cam.ac.uk/~mjfg/ICASSP13_ibm1.pdf
    13 Jun 2013: First, we show score normaliza-tion methodology that improves in average by 20% keyword searchperformance. ... 20–27. [20] X. Cui, J. Xue, X. Chen, P. A. Olsen, P.

  3. IB-interestpoints.dvi

    mi.eng.cam.ac.uk/~cipolla/lectures/PartIB/old/2013-IB-handout2.pdf
    10 May 2013: Sig. nal. Sigma = 20. As σ increases, the signal is smoothed more andmore, and only the central edge survives. ... This discontinuity canbe detected using correlation. 20 Engineering Part IB: Paper 8 Image Matching.

  4. An Explicit Independence Constraint for Factorised Adaptation in…

    mi.eng.cam.ac.uk/~mjfg/wang_is2013.pdf
    13 Jun 2013: System wsj1 dt wsj0 dt wsj0 etMST 23.3 15.7 14.9CAT 20.3 13.3 13.0. ... 20, no. 6, pp. 1713–1724, 2012. [8] J. Latorre, V. Wan, M.

  5. A HIGH-PERFORMANCE CANTONESE KEYWORD SEARCH SYSTEM

    mi.eng.cam.ac.uk/~mjfg/ICASSP13_ibm2.pdf
    13 Jun 2013: 20, no. 8, pp. 2252–2264, 2012. [10] H. Soltau, G. Saon, and B. ... Interspeech, 2011, pp. 1433–1436. [20] D. Can, E. Cooper, A. Sethy, C.

  6. KERNELIZED LOG LINEAR MODELS FOR CONTINUOUS SPEECH RECOGNITION…

    mi.eng.cam.ac.uk/~mjfg/Kernel/sxz20_icassp13.pdf
    27 Mar 2013: Here, the HMM parameters λ associatedwith the kernel k are modified to represent the target acousticenvironment [20]. ... To compare with previouslypublished results, this paper follows the same setup in [20],including the configurations of MFCCs and

  7. paper.dvi

    mi.eng.cam.ac.uk/~mjfg/flego_icassp12.pdf
    13 Jun 2013: The same trends phone-. System A B C D avgVAT 8.1 13.5 11.6 20.5 15.98.

  8. draft21.dvi

    mi.eng.cam.ac.uk/~mjfg/ASRU13.pdf
    7 Nov 2013: Pashto 104 12 44 20 28 20. Turkish 105 10 42 26 19. ... and Language Processing, vol. 20, no. 3, pp. 875–887, 2012. [31] S.

  9. A CONFIDENCE-BASED APPROACH FOR IMPROVING KEYWORD HYPOTHESIS SCORES…

    mi.eng.cam.ac.uk/~mjfg/seigel_ICASSP2013.pdf
    13 Jun 2013: The model alsoallows for continuous features to be represented using spline featurefunctions [20], which have been shown to yield good performancefor confidence estimation with CRFs in previous work [16]. ... 45, no. 1-3, pp. 503–528, Aug. 1989. [20]

  10. Infinite Support Vector Machines in Speech Recognition Jingzhou Yang, …

    mi.eng.cam.ac.uk/~mjfg/yang_is2013.pdf
    13 Jun 2013: Thesampling process of all other parameters is similar to the meth-ods discussed in [14, 19, 20]. ... 9, no. 2, pp. 249–265, 2000. [20] Carl Edward Rasmussen and Zoubin Ghahramani, “Infinite mix-tures of Gaussian process experts,” in NIPS, 2001, pp.

  11. paper.dvi

    mi.eng.cam.ac.uk/~mjfg/wang_is2012.pdf
    13 Jun 2013: add. — VTS RVTSJ. —clean 7.1 6.9 7.3rest. 60.0 19.5 20.0.

Refine your results

clear all

Date

Search history

Recently clicked results

Recently clicked results

Your click history is empty.

Recent searches

Recent searches

Your search history is empty.