Search

Search Funnelback University

Search powered by Funnelback
101 - 150 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. Experiments in Broadcast News Transcription

    mi.eng.cam.ac.uk/reports/full_html/woodland_icassp98.html/
    1 Mar 2000: 24.4. F5. 28.6. 23.8. 27.1. 26.5. FX. 58.5. 55.2. 56.8. 55.0. ... 39.6. 25.1. 37.2. F4. 24.1. 24.7. 24.5. 22.6. F5. 27.6. 25.8.
  3. Segment Generation and Clustering in the HTK Broadcast News…

    mi.eng.cam.ac.uk/reports/full_html/hain_darpa98.html/
    1 Mar 2000: S. 0.56. 98.24. 1.20. T. 0.00. 1.19. 98.81. a). M. S.
  4. Evermann, Kim, Wang, Woodland et al.: CU-HTK Fast System ...

    mi.eng.cam.ac.uk/research/projects/EARS/pubs/evermann_rt03s.pdf
    23 Jun 2003: 0 26.1 23.7P3.3-cn 20.4 24.3 26.6 24.0final 19.9 23.5 25.8 23.3. ... 320xRT 2002† 19.8 24.3 27.0 23.910xRT 2002† 22.3 27.7 31.0 27.2 14%.
  5. A Method for Direct Audio Search with Applications to Indexing and…

    mi.eng.cam.ac.uk/reports/full_html/johnson_icassp00.html/
    16 Jun 2000: Of the 110 seconds worth of news'' rejected by the system with shorter windows, 24 seconds was due to an interview with Bill Clinton being re-broadcast, and the rest was
  6. 3 Nov 2023: 24] Semi-supervised pre-training and back-translation fine-tuning for translation of formal and informal text.
  7. Class-based language model adaptation using mixtures ofword-class…

    mi.eng.cam.ac.uk/reports/svr-ftp/moore_icslp00.pdf
    2 Nov 2000: 1003 250 - 225.85 192.66 224.24 187.371003 250 158.98 151.15 158.68 149.371003 500 - 230.96 193.86 228.93 188.111003 500 159.77
  8. The CUHTK-Entropic 10xRT Broadcast News Transcription System

    mi.eng.cam.ac.uk/reports/full_html/odell_darpa99.html/
    1 Mar 2000: Comparing Table 4 with Table 3 the advantage of including two passes can clearly be seen: on BNeval98 the error rate was reduced by 24% while the overall computation was increased
  9. Speaker Diarisation for Broadcast News

    mi.eng.cam.ac.uk/reports/full_html/tranter_odyssey04.html/
    14 Jun 2004: 9.1. 25.54. 29.7. 46.14. CU. MIT. 2.1. 2.5. 5.3. 24.23. 24.7. ... Adv. Seg. Clust. Score. Metric. NONE. CUED. MIT. 24.23. Primary. CUED_TDT4.
  10. Model-Based 3D Tracking of an Articulated Hand B. Stenger ...

    mi.eng.cam.ac.uk/reports/svr-ftp/stenger_cvpr01.pdf
    12 May 2003: This paper presents a methodfor hand tracking that estimates the pose of a 3D hand modelconstructed from truncated quadrics by using an UnscentedKalman filter [18, 24]. ... Originally published in1952. [24] E. A. Wan and R. van der Merve.
  11. Spoken Document Retrieval for TREC-8 at Cambridge University

    mi.eng.cam.ac.uk/reports/full_html/johnson_trec8.html/
    30 Mar 2000: 24.7. 35.5. 10181. Windowing - 30s@15s. 33.9. 46.1. 18669. Windowing - 30s@10s. ... 55.73. 52.75. 43.89. ----. Sheffield. 32.0. 44.7. 60.66. 52.85. 42.47. 38.24.
  12. Stradwin files

    mi.eng.cam.ac.uk/~gmt11/stradwin/stradwin_files.htm
    RES_VID_GREY_THRESH. long. 24. IMAGE. When recording Doppler data, the intensity threshold (as an 8-bit integer) below which a colour video signal is regarded as being grey-scale.
  13. Spoken Document Retrieval for TREC-9 at Cambridge University

    mi.eng.cam.ac.uk/reports/full_html/johnson_trec9.html/
    23 Feb 2002: 183k articles in [24]), in previous work we found that increasing the parallel corpus size to approximately 110k articles did not help performance [16]. ... 45.02. cr-limsi2. 21.2. 37.24. 39.28. 41.62. 44.12. cr-limsi1. 21.5. 36.56. 38.57.
  14. Clinically Practical Freehand Three-Dimensional Ultrasound

    mi.eng.cam.ac.uk/research/projects/cp3dus/
    22 Jul 2010: Achievements. Freehand RF 3D ultrasound acquisition. We have successfully developed the real-time, RF 3D ultrasound acquisition system [24]. ... 24] G. Treece, R. Prager and A. Gee. Freely available software for 3D RF ultrasound.
  15. Class-based language model adaptation using mixtures of word-class…

    mi.eng.cam.ac.uk/reports/full_html/moore_icslp00.html/
    2 Nov 2000: 225.85. 192.66. 224.24. 187.37. 1003. 250. 158.98. 151.15. 158.68. 149.37.
  16. 9 Jul 2024: Improving Abstractive Summarizationand Information Consistency Assessment. Potsawee Manakul. Department of EngineeringUniversity of Cambridge. This dissertation is submitted for the degree ofDoctor of Philosophy. St John’s College February 2024.
  17. Audio Indexing and Retrieval of Complete Broadcast News Shows

    mi.eng.cam.ac.uk/reports/full_html/johnson_riao00.html/
    19 Apr 2000: 39.39. 27.42. 752913. -. -. N. B. 95.8. 37.52. 24.92. 698461. -. -. ... In Proc. TREC-7, NIST SP 500-242, pages 1-24, Gaithersburg, MD.
  18. LARGE SCALE MMIE TRAINING FOR CONVERSATIONAL TELEPHONE SPEECH…

    mi.eng.cam.ac.uk/reports/full_html/woodland_stw00.html/
    5 Oct 2000: The bigram 1-best hypotheses had a 24.6% word error rate (WER) and a Lattice WER (LWER) of 6.2%...
  19. 20 Feb 2018: Trial # users average # calls median # callsAMT 140 6.5 2Cambridge 17 24.4 20. ... vol. 24, no. 2, pp.150–174, 2010. [7] Amazon, “Amazon Mechanical Turk,” 2011.
  20. The Cambridge University March 2005 Speaker Diarisation System

    mi.eng.cam.ac.uk/reports/full_html/sinha_eurospeech05.html/
    22 Sep 2005: The experiments reported in this paper use a development set of 24 US broadcast news shows, denoted.
  21. Uncertainty: Knowing What You Don't Know

    mi.eng.cam.ac.uk/~mjfg/mjfg_cncc2021.pdf
    20 Jun 2023: 24/36. Spoken Language Assessment. 25/36. Grader Uncertainty: Ensemble-Based. Within 0.5 CEFR-Level Within 1.0 CEFR-Level26/36.
  22. Shape Context and Chamfer Matching in Cluttered Scenes A. ...

    mi.eng.cam.ac.uk/reports/svr-ftp/thayananthan_cvpr03.pdf
    12 May 2003: Belongie,J. Malik, and J. Puzicha. Shapematchingandobjectrecognitionusingshapecontexts. IEEE Trans.PatternAnalysisand Machine Intell., 24(4):509–522,April 2002.
  23. Part Name Part Image Part Weight [mg] Electric, Motor ...

    mi.eng.cam.ac.uk/IALego/helicopter_files/helicopter_weights.pdf
    1 Jan 2024: 1300. Light Bluish Gray Technic, Gear 24 Tooth (New Style. with Single Axle Hole).
  24. MultiMedia Document Retrieval (1997-2000) - Progress

    mi.eng.cam.ac.uk/research/projects/Multimedia_Document_Retrieval/progress.html
    7 Oct 2001: The overall word error rate for the data was 24.8%, the lowest in the TREC-7 SDR evaluation, with the baselines provided by NIST offering 33 and 42%. ... The final project publications include the TREC-9 paper [24] , two papers in the International
  25. 9 Nov 2023: Talk. [24] Context-dependent alignment models and hierarchical phrase-based translation with weighted finite state trans-ducers, GALE PI Meeting, Tampa, FL, USA, May 2009. ... Association for Computational Linguistics, November 2021. [24] BO-HSIANG TSENG,
  26. 20 Feb 2018: error rate of 33.2 %, and for the first and secondorder derivatives the error rates of the classifiers are 33.1 %and 24.2 %, respectively. ... 24.8 42.4par 22.7 13.1 21.7 32.4 32.7 25.2 27.4 45.1.
  27. paper.dvi

    mi.eng.cam.ac.uk/~mjfg/wang_icassp13.pdf
    13 Jun 2013: 2011, pp. 24–29, Ieee. [13] M. J. F. Gales and F.
  28. DEVELOPMENT OF THE 2003 CU-HTK CONVERSATIONAL TELEPHONE…

    mi.eng.cam.ac.uk/reports/svr-ftp/evermann_icassp2004.pdf
    27 May 2004: purpose WER. P1 supervision for VTLN 34.2P2 supervision for MLLR 28.4P3 lattice generation 24.8. ... System (P4) A B C DSAT HLDA SPron non-HLDA23.0 23.6 23.4 24.8.
  29. 19 Dec 2006: Uncertainty 1 4 16 256. Clean — 33.2. SPLICENo. 24.6 20.7 17.0 12.3FE-CMLLR 16.3 15.3 12.8 13.5.
  30. Bin Jia, Khe Chai Sim et al: CU-HTK RT03 ...

    mi.eng.cam.ac.uk/research/projects/EARS/pubs/jia_rt03s.pdf
    23 Jun 2003: Automatic Segmentation. Segmentation Diarisation CER (%)MS FA Tot. Manual 1.2 24.5 25.6 49.8Automatic 3.7 8.3 11.9 50.8.
  31. Improving Attention-based Sequence-to-sequence Models

    mi.eng.cam.ac.uk/~mjfg/thesis_qd212.pdf
    5 Jul 2022: previoustokens. To achieve more accurate estimation, sequence-to-sequence models are usuallyautoregressive [24]. For autoregressive models, a standard approach is teacher forcing, which guides a modelwith reference output history during training.
  32. THE DEVELOPMENT OF THE CAMBRIDGE UNIVERSITY RT-04 DIARISATION SYSTEM…

    mi.eng.cam.ac.uk/reports/svr-ftp/tranter_rt04.pdf
    10 Jan 2005: show. (b) Mean DER across all 24 development shows whenonly including c0 in clustering if the mean value is above a criticalthreshold. ... RT-04 RT-04 RT-04 23.86 24.12. Table 12. Progress since RT-03s on theeval04f data.
  33. 20 Feb 2018: THE HIDDEN INFORMATION STATE SYSTEMA block diagram of the HIS system is shown in Figure 13 [23], [24]. ... The history states record grounding and query status information but the details are not relevant here (see [24]).
  34. 20 Feb 2018: U| 103 and |M| 103. (24). Goals are composed ofNC constraints taken from theset of constraintsC, andNR requests taken from the setof requestsR.
  35. The Cambridge Multimedia Document Retrieval (MDR) Project : Summary…

    mi.eng.cam.ac.uk/reports/full_html/sparckjones_cltr517.html/
    10 Oct 2001: X) 64.95 61.25 46.82 45.24 44.27 30.33 39.98 42.14 38.65 35.72 BE DBRF2 (X) 66.57 65.89 45.21 ... BE DBRF (X) 69.41 69.12 52.55 51.73 51.14 36.86 41.99 44.13 42.14 42.05 BE [PR]BRF (A) 66.24 64.53
  36. LARGE SCALE DISCRIMINATIVE TRAINING FORSPEECH RECOGNITION P.C.…

    mi.eng.cam.ac.uk/reports/svr-ftp/woodland_asr00.pdf
    6 Nov 2000: Some discriminative training schemes, such as frame-discrimination [14, 24], try to over-generate training set con-fusions to improve generalisation. ... In [24] it was shownthat the improvements obtained by FD were at least as goodas those reported by
  37. Deep Learning for Speech Recognition

    mi.eng.cam.ac.uk/~mjfg/LxMLS17.pdf
    29 Nov 2017: Network Interpretation [24]. Standard /ay/ Stimulated /ay/. • Deep learning usually highly distributed - hard to interpret• awkward to adapt/understand/regularise• modify training - add stimulation regularisation• improves ASR performance.
  38. MORTGAGE DEFAULT: CLASSIFICATION TREES ANALYSIS David Feldman* and…

    mi.eng.cam.ac.uk/~mjfg/local/4F10/Feldman_Gross.pdf
    15 Nov 2005: MORTGAGE DEFAULT: CLASSIFICATION TREES ANALYSIS. David Feldman and Shulamith Gross#. March 24, 2003. ... 24. robust Cross-Validation method. Since it does not have any particular.
  39. Unsupervised Bayesian Detection of Independent Motion in Crowds…

    mi.eng.cam.ac.uk/reports/svr-ftp/brostow_MotionInCrowdsCVPR06.pdf
    14 Sep 2006: 24, 18]. Both systems group an image’sspatial features, performing a global annealing optimizationthat propagates the certainty at distinct person-boundaries touncertain areas where those people’s outlines are ambigu-ous. ... 24] P. Tu and J.
  40. Mark John Francis Gales Thesis, Book Chapters and Magazines ...

    mi.eng.cam.ac.uk/~mjfg/publications_list.pdf
    11 Oct 2023: Audio Speech Lang.Process., vol. 24, no. 8, pp. 1438–1449, 2016. 9. ... Signal Processing,ICASSP 2015, South Brisbane, Queensland, Australia, April 19-24, 2015, pp.
  41. 7 Oct 2001: 8;,=&"vZ$9V K)i!Zi9V ;)Î$9h ;& ;=!"p;) / -,H;&AP,!#P6 %S+[#( 24 )g(>@{7cPU(.( 7;'8;(! ... 9V @24 Ì ' $;S+[ -c.,=",=&8U - PU -"P7,=!)G,=&,=&,H&8g- / -( -,=,Hg",=-;' - -r( -,!K9$(-v> zXx}24 & -)g=![] Ç4',!
  42. ICSLPDataCollection-10

    mi.eng.cam.ac.uk/~sjy/papers/wiyo04b.pdf
    20 Feb 2018: Per-turn. WER. Per-dialog WER. None 2 6 24 83 % 0 % 0 % Low 4 12 48 83 % 32 % 28 % Med 4 12 48 77 % 46 % 41 % Hi 2 6 24 ... Dataset. Metrics (task & user sat). R2 Significant predictors. ALL User-S 52 % 1.03 Task ALL User-C 60 % 5.29 Task – 1.54
  43. The Effect of Cognitive Load on a Statistical Dialogue ...

    mi.eng.cam.ac.uk/~sjy/papers/gtht12.pdf
    20 Feb 2018: Computer Speech and Language,24(4):562–588. O Tsimhoni, D Smith, and P Green. ... Computer Speech andLanguage, 24(2):150–174.
  44. 20 Feb 2018: wwpos 24.52 11.29 18.47wspos 11.33 4.91 3.31wpof s 1.13 4.82 8.82wppof s 24.27 6.49 10.54wonset 15.08 0.33 ... 47.3% 52.7%. 75.3% 24.7%. Figure 3: Categorical quality ratings for spectral conversion duration conversion HMM-based contour generation.
  45. 20 Feb 2018: POMDP-based Hidden Information State (HIS) DialogueSystem [22, 24]. ... of ICASSP, Honolulu, HI, 2007. [24] B. Thomson, J. Schatzmann, K.
  46. 20 Feb 2018: 3.3. The agenda-based simulated user. The agenda-based user simulator [24, 25] factorises the user stateinto an agenda and a goal. ... 23] TopTable, “TopTable,” 2012, https://www.toptable.com. [24] J Schatzmann, Statistical User and Error Modelling
  47. 20 Feb 2018: 1.2% 2.0%Request 17.4% 24.5% 18.4% 24.4%. ... 24, no. 4, pp. 562–588, 2010. [22] J Peters and S Schaal, “Natural Actor-Critic,” Neurocomput-ing, vol.
  48. POLICY COMMITTEE FOR ADAPTATION IN MULTI-DOMAIN SPOKEN…

    mi.eng.cam.ac.uk/~sjy/papers/gmsv15.pdf
    20 Feb 2018: 24, no. 2, pp. 395–429, Apr. 2010. [8] Pierre Lison, “Multi-policy dialogue management,” inProceedings of the SIGDIAL 2011 Conference, Strouds-burg, PA, USA, 2011, SIGDIAL ’11, pp. ... 24, no. 4,pp. 562–588, 2010. [18] T Jebara, R Kondor, and A
  49. 20 Feb 2018: In control tests by humanusers, the success rate of the system was 24.5% higher thanthe baseline Lets Go! ... Com-pared to the BASELINE system, the BUDSLETSGO systemimproves the dialogue success rate by 24.5% and the worderror rate by 9.7%.
  50. 20 Feb 2018: The static feature set comprised 24 Mel-Cepstral coefficients,logarithm of F0 and aperiodic energy components in five frequency. ... 12 sentences werethen randomly selected to make up a testset for each listener, leadingto 24 wave files pairs (12 for
  51. 20 Feb 2018: Corpus Mean (SD) Grades Correlationn Human Auto R p. L 21 24.2 (3.1) 17.1 (1.9). ... 69C 50 24.0 (3.0) 15.6 (3.3). 59. 01. Table 2: Mean (standard deviation) of human andautomated grades, along with Pearson’s correla-tions between the human and

Search history

Recently clicked results

Recently clicked results

Your click history is empty.

Recent searches

Recent searches

Your search history is empty.