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 - 9 of 9 search results for KaKaoTalk:vb20 200 |u:mi.eng.cam.ac.uk where 0 match all words and 9 match some words.

  1. Results that match 1 of 2 words

  2. Machine Learning of Level and Progression in Second/Additional…

    mi.eng.cam.ac.uk/~kmk/presentations/UBham_May2016_Knill.pdf
    12 May 2016: A1 A2 B1 B2. 0. 200. 400. 600. 800. 1000. 0 2 4 6 8 10 12 14 16. ... System HL-dim Training Data. % Error. KNN - SUP 20.8 RNNLM 100 17.5 RNNLM 200 Semi-SUP 9.3.

  3. SYSTEM COMBINATION WITH LOG-LINEAR MODELS J. Yang, C. Zhang, ...

    mi.eng.cam.ac.uk/~mjfg/yang_ICASSP16.pdf
    12 Jul 2016: Parameter updates were averagedover a mini-batch with 200 frames and were smoothed by adding a“momentum” term of 0.9 times the previous updates.

  4. Knill_IS2014_slides.dvi

    mi.eng.cam.ac.uk/~kmk/presentations/Interspeech2014_Sep14_Knill.pdf
    12 May 2016: 0 200 400 600 800 1000 12000. 0.1. 0.2. 0.3. 0.4.

  5. System Combination with Log-linear Models

    mi.eng.cam.ac.uk/~mjfg/icassp16_yang.pdf
    5 Apr 2016: Parameter updates were averagedover a mini-batch with 200 frames and were smoothed by adding a“momentum” term of 0.9 times the previous updates.

  6. Machine Learning of Level and Progression in Spoken EAL ...

    mi.eng.cam.ac.uk/~kmk/presentations/CEP_Feb2016_Knill.pdf
    12 May 2016: Speaking Time Versus Learner Progression. 0. 100. 200. 300. 400. 500.

  7. 4F10: Deep Learning

    mi.eng.cam.ac.uk/~mjfg/local/4F10/lect6.pdf
    8 Nov 2016: 20. 40. 60. 80. 100. 120. 140. 160. 180. 200. 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 10. ... 200. 400. 600. 800. 1000. 1200. 1400. 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 10.

  8. Investigation of back-off based interpolation between Recurrent…

    mi.eng.cam.ac.uk/~mjfg/asru15-chen.pdf
    11 Mar 2016: A total of 200 hidden units were used. RNNLMs weretrained on GPU as described in [25].

  9. Deep Learning for Speech Processing - An NST Perspective

    mi.eng.cam.ac.uk/~mjfg/NST_2016.pdf
    29 Sep 2016: TTS: Bottleneck Features [49]. 0 50 100 150 200 250 300 350.

  10. Structured and InûniteDiscriminative Models for Speech Recognition…

    mi.eng.cam.ac.uk/~mjfg/thesis_jy308.pdf
    26 Jul 2016: Structured and InûniteDiscriminative Models for. Speech Recognition. Jingzhou YangHomerton College. Department of Engineering. University of Cambridge. A thesis submitted to the University of Cambridge for the degree of. Doctor of Philosophy.

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.