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 28 search results for katalk:za33 24 |u:mi.eng.cam.ac.uk where 0 match all words and 28 match some words.

  1. Results that match 1 of 2 words

  2. Discriminative Models for Speech Recognition Mark Gales 1 February ...

    mi.eng.cam.ac.uk/~mjfg/talk_ita.pdf
    22 Feb 2007: 3-emitting state HMMs. ClassifierTraining Componentsλ α 10 20. HMM ML – 29.4 27.3C-Aug ML CML 24.2 –. HMM MMI – 25.3 24.8C-Aug MMI CML 23.4 –.

  3. IEEE TRANS. ON SAP, VOL. ?, NO. ??, ????? ...

    mi.eng.cam.ac.uk/research/projects/AGILE/publications/kai_ASP07.pdf
    10 Oct 2007: It is also interesting to compare N-Best supervisionto the standard 1-Best supervision adaptation approaches suchas iterative MLLR [24]. ... Zθ(O, H)can be simply calculated using the forward algorithm withp̃(ot|θt),. Zθ(O, H) =. θ. P (θ|M). t.

  4. journal.dvi

    mi.eng.cam.ac.uk/~mjfg/kcs_csl.pdf
    4 Apr 2007: Vector linear prediction (VLP) is also a trajectory model [24], where the stateoutput probability of ot is conditionally independent of other parameters giventhe current state, qt, and observation dependencies, Ht. ... In addition, a novel. 24. approach

  5. Discriminative Complexity Control and Linear Projections for Large…

    mi.eng.cam.ac.uk/~mjfg/thesis_xl207.pdf
    16 Nov 2007: 2.5 HLDA and LDA projection 24. 2.6 multiple HLDA projections 25.

  6. IEEE Proo f IEEE TRANSACTIONS ON AUDIO, SPEECH, AND ...

    mi.eng.cam.ac.uk/~mjfg/kai_ASP06.pdf
    4 Apr 2007: The log prior may be expressed as. (24). where is the general form defined in (15). ... 24] M. J. F. Gales, “Acoustic factorization,” presented at the ASRU Conf.,2001.

  7. PhD Thesis

    mi.eng.cam.ac.uk/~mjfg/thesis_kcs23.pdf
    16 Nov 2007: 2.3 Limitations of HMMs for Speech Recognition 24. 2.3.1 Explicit Temporal Correlation Modelling 25.

  8. Real-time Freehand 3D Ultrasound Calibration P-W. Hsu, R. W. ...

    mi.eng.cam.ac.uk/reports/svr-ftp/hsu_tr565.pdf
    19 Feb 2007: H. Berman. Engineering a freehand 3D ultrasoundsystem. Pattern Recognition Letters, 24:757–777, 2003. ... Ultrasound in Medicine & Biology, 24(6):855–869, 1998. R. W. Prager, A.

  9. A Gaussian Mixture Model Spectral Representation for Speech…

    mi.eng.cam.ac.uk/~mjfg/thesis_mns25.pdf
    16 Nov 2007: 2.5.1 Vocal tract length normalisation 24. 2.5.2 Maximum likelihood linear regression 25. ... $ I / (2.23)3 /. $ $ I $ I - $ (2.24) $F 3 3 % / (2.25).

  10. ATK An Application Toolkit for HTK Version 1.6 Steve ...

    mi.eng.cam.ac.uk/research/dialogue/ATK_Manual.pdf
    20 May 2007: TARGETKIND = MFCC_E_D_N_A. TARGETRATE = 100000.0. USEPOWER = F. NUMCHANS = 24. ... 24. void ATask::FooCmd(). {. int i;. if (GetIntArg(i,0,100)) {. // implement foo(i). }. }.

  11. Linear Gaussian Models for Speech Recognition Antti-Veikko Ilmari…

    mi.eng.cam.ac.uk/~mjfg/thesis_avir2.pdf
    16 Nov 2007: 3.1 State Space Models 24. 3.2 Bayesian Networks 25. 3.3 State Evolution Process 27. ... bank of triangular filters (eg. 24 channels). This smoothed power spectrum is compressed using.

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.