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 35 search results for TALK:PC53 20 |u:mi.eng.cam.ac.uk where 0 match all words and 35 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: LanguageTraining. ML MPE. English (WER%) 16.0 13.1Arabic (WER%) 22.9 20.0. Mandarin (CER%) 14.4 12.7. ... 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. paper.dvi

    mi.eng.cam.ac.uk/~mjfg/liao_ICASSP07.pdf
    15 Aug 2007: Compensation Noise Est. Type %WER. None — 20.8. JointML VTS 19.1ML Joint 18.8. ... The best training scheme was. the JAT system, which exceeded matched and multistyle with VTSperformance at both 20 and 14 dB SNR.

  4. UNSUPERVISED TRAINING FOR MANDARIN BROADCAST NEWS AND…

    mi.eng.cam.ac.uk/~mjfg/wang_ICASSP07.pdf
    22 Jun 2007: Two thresholds were used in the show level selection. The firstwas a show-level confidence score of 55%, the second a thresholdof 20% for the percentage of English. ... The gains from using discriminative training weremuch reduced. MPE unsupervised

  5. SPEECH RECOGNITION SYSTEM COMBINATION FOR MACHINE TRANSLATION M.J.F.…

    mi.eng.cam.ac.uk/~mjfg/gales_ICASSP07.pdf
    22 Jun 2007: In addition a maximum segmentlength of 20 seconds was imposed by splitting longer segments atthe longest inter-word gap. ... System Comb. CER%level bnmd06 bcmdr06CU — 8.0 21.8BBN 8.6 23.9BBNCU — 7.5 20.7CUBBN char 7.1 21.3.

  6. PREDICTIVE LINEAR TRANSFORMS FOR NOISE ROBUST SPEECH RECOGNITION…

    mi.eng.cam.ac.uk/~mjfg/gales_ASRU07.pdf
    15 Aug 2007: Here. Σ(m)-1 = A(r)TΣ̃(m)-1diag A. (r) (20). and Σ̃(m)diag is a diagonal covariance matrix. ... System # iter SNR(dB)20 15 10 50 31.2 50.4 79.2 89.7.

  7. Discriminative Models for Speech RecognitionM.J.F. Gales Cambridge…

    mi.eng.cam.ac.uk/~mjfg/mjfg_ita.pdf
    22 Feb 2007: m=1. γjm(t) (20). For the second derivative,. ckn Tcjm log(p(O1:T ; λ)) = (21)1. ... model. No data or feature whitening was performed. Classifier Criterion Componentsλ α 10 20.

  8. UNSUPERVISED TRAINING FOR MANDARIN BROADCAST NEWS AND…

    mi.eng.cam.ac.uk/research/projects/AGILE/publications/wang_ICASSP07.pdf
    10 Oct 2007: Two thresholds were used in the show level selection. The firstwas a show-level confidence score of 55%, the second a thresholdof 20% for the percentage of English. ... The gains from using discriminative training weremuch reduced. MPE unsupervised

  9. Unsupervised Language Model Adaptation for Mandarin…

    mi.eng.cam.ac.uk/reports/svr-ftp/mrva_icslp06.pdf
    20 Jan 2007: BN data and 20 hours of BC data. The language model is describedin section 3.2.

  10. SPEECH RECOGNITION SYSTEM COMBINATION FOR MACHINE TRANSLATION M.J.F.…

    mi.eng.cam.ac.uk/research/projects/AGILE/publications/gales_ICASSP07.pdf
    10 Oct 2007: In addition a maximum segmentlength of 20 seconds was imposed by splitting longer segments atthe longest inter-word gap. ... System Comb. CER%level bnmd06 bcmdr06CU — 8.0 21.8BBN 8.6 23.9BBNCU — 7.5 20.7CUBBN char 7.1 21.3.

  11. Discriminative Models for Speech RecognitionM.J.F. Gales Cambridge…

    mi.eng.cam.ac.uk/~mjfg/mjfg_ita_margin.pdf
    30 May 2007: Tl(w) = log (P (w)) (20). and constrain all the α’s associated with this for all models tobe the same, αl. ... model. No data or feature whitening was performed. Classifier Criterion Componentsλ α 10 20.

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.