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 14 search results for `broadcast news` |u:mi.eng.cam.ac.uk

  1. Fully-matching results

  2. PowerPoint プレゼンテーション

    mi.eng.cam.ac.uk/UKSpeech2017/posters/e_tsunoo.pdf
    3 Jul 2018: Our Proposal. news stream divided stories. Hierarchical Recurrent Neural Network (HRNN). • ... To capture a hierarchical character of broadcast news - each story consists of multiple sentences - each sentence consists of words which are relevant to the

  3. INDICATOR VARIABLE DEPENDENT OUTPUT PROBABILITY MODELLING…

    mi.eng.cam.ac.uk/~sjy/papers/tuyo01.pdf
    20 Feb 2018: The following recognition experiments were conducted onthe 1997 Broadcast News task [5] by rescoring tri-gram lat-tices. ... Different topologies of themodel were evaluated on the 1997 Broadcast News task andsome small improvements were obtained.

  4. paper.dvi

    mi.eng.cam.ac.uk/~ar527/ragni_is2018a.pdf
    15 Jun 2018: Mrva, R. Sinha, andS. E. Tranter, “Progress in the CU-HTK broadcast news transcrip-tion system,”IEEE TSAP, vol. ... Xiang, S. Abdou, and J. Makhoul, “Re-cent progress in Arabic broadcast news transcription at BBN,” inInterspeech, 2005.

  5. Structured Deep Neural Networks for Speech Recognition

    mi.eng.cam.ac.uk/~mjfg/thesis_cw564.pdf
    12 Jul 2018: 139. 7.9 Broadcast News: Recognition performance (WER %) of CE MBANNwith i-vector predictive model. ... AM Acoustic Model. ASR Automatic Speech Recognition. BN Broadcast News. CE Cross Entropy.

  6. ./plot_entropy.eps

    mi.eng.cam.ac.uk/~ar527/chen_is2017.pdf
    15 Jun 2018: The performance of the bi-RNNLMs is evaluatedon three speech recognition tasks: broadcast news; meetingtran-scription (AMI); and low-resource systems (Babel data). ... 5. EXPERIMENTS. The performance of the bi-RNNLMs was evaluated on three cor-pora:

  7. poyosp08

    mi.eng.cam.ac.uk/~sjy/papers/dpyo08.pdf
    20 Feb 2018: Gales, D. Mrva, K.C. Sim and P.C. Woodland, “Development of. the CU-HTK 2004 Broadcast News Transcription.

  8. tech.dvi

    mi.eng.cam.ac.uk/~sjy/papers/bghk13.pdf
    20 Feb 2018: likelihood. Otherclassifiers such as SVMs [13] and MLPs [14] have also been used.This classification approach has been used successfully in LVCSRtasks such as meetings [15, 14, 16] and broadcast news ... 17] J.L. Gauvain, L. Lamel, and G. Adda,

  9. Impact of ASR Performance on Free Speaking Language Assessment ...

    mi.eng.cam.ac.uk/~ar527/knill_is2018.pdf
    15 Jun 2018: A Kneser-Ney trigram LM is trainedon 186k words from the System 1 training data, and interpolatedwith a general LM trained on Broadcast News English [34], us-ing the SRILM toolkit ... Fiscus, and W. M. Fisher, “Design and Prepa-ration of the 1996 Hub-4

  10. A HIERARCHICAL ATTENTION BASED MODEL FOR OFF-TOPIC SPONTANEOUSSPOKEN…

    mi.eng.cam.ac.uk/~mjfg/ALTA/publications/ASRU2017/HierarchicalAttentionBased/hierarchical-attention-based.pdf
    24 Jan 2018: A Kneser-Ney trigram language model is trainedon this data and interpolated with a general English languagemodel trained on a large broadcast news corpus, using the SRILMtoolkit [16].

  11. Use of Graphemic Lexicons for Spoken Language Assessment K.M. ...

    mi.eng.cam.ac.uk/~ar527/knill_is2017.pdf
    15 Jun 2018: The DNN structure is 702x10005x6000. AKneser-Ney trigram LM is trained on 186K words of BULATStest data and interpolated with a general English LM trained ona large broadcast news corpus, using

Refine your results

clear all

Date

Related searches for `broadcast news` |u:mi.eng.cam.ac.uk

By topic

Search history

Recently clicked results

Recently clicked results

Your click history is empty.

Recent searches

Recent searches

Your search history is empty.