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
51 - 60 of 1,000 search results for katalk:za33 24 |u:mi.eng.cam.ac.uk where 0 match all words and 1,000 match some words.

  1. Results that match 1 of 2 words

  2. A LANGUAGE SPACE REPRESENTATION FOR SPEECH RECOGNITION

    mi.eng.cam.ac.uk/~mjfg/icassp15-ragni.pdf
    18 May 2015: There are many options to select the form of rep-resentation of the clusters and the combination method to employ[18, 17, 13, 24, 25]. ... 20, no. 6, pp. 1713–1724, 2012. [24] V. Diakoloukas and V.

  3. N-BEST ERROR SIMULATION FOR TRAINING SPOKEN DIALOGUE SYSTEMS Blaise…

    mi.eng.cam.ac.uk/~sjy/papers/thgt12.pdf
    20 Feb 2018: 24, no. 4, pp. 562–588, 2010. [3] R. Sutton and A.

  4. EFFECTS OF THE USER MODEL ON SIMULATION-BASEDLEARNING OF DIALOGUE ...

    mi.eng.cam.ac.uk/~sjy/papers/swsy05.pdf
    20 Feb 2018: The COMMUNICATOR systems in contrast onlyrequest between 24% and 43% of the unknown slots in each state.

  5. Applying Deep Learning in Non-native Spoken English Assessment

    mi.eng.cam.ac.uk/~mjfg/ALTA/presentations/APSIPA2019_Knill.pdf
    21 Feb 2022: 1.0 indicates within one CEFR grade-level. 24/45. Assessment System Performance. • ... 1.0 indicates within one CEFR grade-level. 24/45. Performance Analysis. 25/45.

  6. Structured Discriminative Models Using Deep Neural-Network Features

    mi.eng.cam.ac.uk/~mjfg/asru15-vanDalen.pdf
    11 Mar 2016: MPE— 7.15 11.06 14.37 24.54 16.79CML 6.95 11.00 14.29 24.39 16.68large-margin 7.02 10.92 14.16 24.28 ... Therefore the systems use graphemic lex-ica generated using an approach which is applicable to all Unicodecharacters [24].

  7. CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT DISCRIMINATIVE…

    mi.eng.cam.ac.uk/~mjfg/gales_tr605.pdf
    13 Aug 2008: In common with other work in this. 5. area [9, 24], G is approximated by the diagonalised empirical covariance matrix of the trainingdata. ... 00 25.48 21.73 25.95 24.46 21.64 26.05 24.51 22.56.

  8. AUTOMATIC COMPLEXITY CONTROL FOR HLDA SYSTEMS X. Liu, M. ...

    mi.eng.cam.ac.uk/reports/svr-ftp/liu_icassp2003.pdf
    19 Sep 2003: Fig. 1. Test set word error rate for all possible models, with thestandard front-end 12, 16 and 24 component performance. ... The best perfor-mance, 36.8%, was obtained using 24 components per state and anHLDA projection from 52 dimensions to 38

  9. Towards Learning Orientated Assessment for Non-native Learner Spoken…

    mi.eng.cam.ac.uk/~kmk/presentations/ALTA_Sheffield_20190306.pdf
    8 Mar 2019: 300 300. 25.5. 400 24.5. 400 24.4. ASR on Non-native Speech (2). • ... Thai dh d 7.24 oh aa 5.21. 30. • Top 2 recurrent substitution errors for speakers in each L1.

  10. Towards Learning Orientated Assessment for Non-native Learner Spoken…

    mi.eng.cam.ac.uk/~mjfg/ALTA/presentations/ALTA_Sheffield_20190306.pdf
    21 Feb 2022: 300 300. 25.5. 400 24.5. 400 24.4. ASR on Non-native Speech (2). • ... Thai dh d 7.24 oh aa 5.21. 30. • Top 2 recurrent substitution errors for speakers in each L1.

  11. eps.dis.dur.testa.eps

    mi.eng.cam.ac.uk/~mjfg/gales_ASRU09.pdf
    14 Sep 2010: Using 17 pairs, about 24% of thetotal number of pairs, 92% of the WER improvement usingthe 1-v-1 system over the VTS baseline was achieved.

Refine your results

Date

Search history

Recently clicked results

Recently clicked results

Your click history is empty.

Recent searches

Recent searches

Your search history is empty.