Search

Search Funnelback University

Search powered by Funnelback
1 - 10 of 13 search results for KaKaoTalk:vb20 200 |u:mi.eng.cam.ac.uk where 0 match all words and 13 match some words.
  1. Results that match 1 of 2 words

  2. Global Optimisation of Neural Network Models Via Sequential…

    mi.eng.cam.ac.uk/reports/full_html/freitas_icslp98.html/
    8 Mar 2000: 100 samples were used in the Monte Carlo simulations. Table 1 shows the average one-step-ahead prediction errors obtained for 10 runs, of 200 time steps each, on a Silicon
  3. Spoken Document Retrieval for TREC-7 at Cambridge University

    mi.eng.cam.ac.uk/reports/full_html/johnson_trec7.html/
    30 Mar 2000: Postscript Version : Proc. TREC-7, NIST SP 500-242, pp. 191-200 (July 1999). ... Misrecognising every word will in practise give a TER of below 200% as the word ordering is unimportant, so some recognition errors will cancel out.
  4. Spoken Document Retrieval for TREC-8 at Cambridge University

    mi.eng.cam.ac.uk/reports/full_html/johnson_trec8.html/
    30 Mar 2000: Spoken Document Retrieval for TREC-8 at Cambridge University. S.E. Johnson , P. Jourlin ,K. Spärck Jones & P.C. Woodland. Trumpington Street, Cambridge, CB2 1PZ, UK. Pembroke Street, Cambridge, CB2 3QG, UK. Email:. {eng.cam.ac.uk. {cl.cam.ac.uk.
  5. Effects of Out of Vocabulary Words in Spoken Document Retrieval

    mi.eng.cam.ac.uk/reports/full_html/woodland_sigir00.html/
    14 Aug 2000: BRF is run on the parallel collection adding the best 200 new terms taken from the top 10 documents to the original document with a term frequency equal to 1.
  6. LARGE VOCABULARY DECODING AND CONFIDENCE ESTIMATIONUSING WORD…

    mi.eng.cam.ac.uk/reports/svr-ftp/evermann_icassp00.pdf
    5 May 2000: triphone quinphoneHub4 eval’97 0.302 0.163Hub5 dev’98 0.191 -0.026Hub5 eval’98 0.104 -0.200. ... triphone quinphonepost tree post tree. time dep. 0.104 0.234 -0.200 0.188confnet 0.000 0.213 -0.396 0.198.
  7. GLOBAL OPTIMISATION OF NEURAL NETWORK MODELSVIA SEQUENTIAL…

    mi.eng.cam.ac.uk/reports/svr-ftp/freitas_icslp98.pdf
    10 Apr 2000: 100 samples were used in theMonte Carlo simulations. Table 1 shows the average one-step-ahead prediction er-rors obtained for 10 runs, of 200 time steps each, on aSilicon Graphics ... 10. 12. 34. 0. 50. 100. 150. 2000. 100. 200. 300.
  8. Submitted in partial requirement for the MPhil in Computer ...

    mi.eng.cam.ac.uk/reports/svr-ftp/johnson_mthesis.pdf
    10 Apr 2000: Table 7: Model-based MLLR transform Matrices results. 0 5 10 15 200. ... Figure 11: Dendograms for Neighbourhood Clustering Methods. 0 25050 100 150 200.
  9. Reducing Word Error Rates of Found Speech -XPERT Tool ...

    mi.eng.cam.ac.uk/reports/svr-ftp/johnson_tr330.pdf
    10 Apr 2000: C,"understand","understand",413.300413.880:C,"why","why",413.880414.080:C,"it","it",414.080414.200:C,"makes","makes",414.200414.420:C,"a","a",414.420414.490:C,"
  10. SPOKEN DOCUMENT RETRIEVAL FOR TREC-7 AT CAMBRIDGE UNIVERSITY S.E. ...

    mi.eng.cam.ac.uk/reports/svr-ftp/johnson_trec7.pdf
    8 Mar 2000: Note, not producing any output gives a TER of 100%whereas misrecognising every word as on OOV word produces a TERof 200%, due to each substitution error counting as both an ... Misrecognising every word will in practise givea TER of below 200% as the
  11. SPOKEN DOCUMENT RETRIEVAL FOR TREC-8 AT CAMBRIDGE UNIVERSITY S.E. ...

    mi.eng.cam.ac.uk/reports/svr-ftp/johnson_trec8.pdf
    10 Apr 2000: SPOKEN DOCUMENT RETRIEVAL FOR TREC-8 AT CAMBRIDGE UNIVERSITY. S.E. Johnson†, P. Jourlin‡, K. Sp̈arck Jones‡ & P.C. Woodland†. †Cambridge University Engineering Department,Trumpington Street, Cambridge, CB2 1PZ, UK.Email: {sej28,pcw

Refine your results

Search history

Recently clicked results

Recently clicked results

Your click history is empty.

Recent searches

Recent searches

Your search history is empty.