Search
Search Funnelback University
- Refined by:
- Date: 2000
1 -
40 of
40
search results for TALK:Vb20 24 / |u:mi.eng.cam.ac.uk
where 0
match all words and 40
match some words.
Results that match 1 of 2 words
-
Class-based language model adaptation using mixtures ofword-class…
mi.eng.cam.ac.uk/reports/svr-ftp/moore_icslp00.pdf2 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 -
LARGE SCALE DISCRIMINATIVE TRAINING FORSPEECH RECOGNITION P.C.…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_asr00.pdf6 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 -
Improving Retrieval on Imperfect Speech Transcriptions
mi.eng.cam.ac.uk/reports/full_html/jourlin_sigir99.html/8 Mar 2000: HTK. ATT. Dragon. Base1. Sheff. Base2. DERA. WER. 24.8. 31.0. 29.8. -
The Cambridge University Spoken Document Retrieval System
mi.eng.cam.ac.uk/reports/full_html/johnson_icassp99.html/8 Mar 2000: Sheffield. 39.8. 37.6. 37.1. 34.6. HTK-1. 28.6. 24.9. 24.7. 22.2. HTK-2. ... 24.1. 21.5. 21.2. 18.7. Table 3: Story-based % Word Error Rates for TREC-6 data. -
The 1998 HTK Broadcast News Transcription System: Development and…
mi.eng.cam.ac.uk/reports/full_html/woodland_darpa99.html/2 Mar 2000: F5. 24.4. 23.8. 21.4. 20.0. FX. 32.7. 32.7. 30.9. 30.9. Overall. ... 19.1. 17.2. 24.7. 30.9. P3. bg. 1/N. 19.1. 11.9. 20.4. 27.6. -
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. -
The 1997 HTK Broadcast News Transcription System
mi.eng.cam.ac.uk/reports/full_html/woodland_darpa98.html/1 Mar 2000: 24.6. F5. 28.6. 23.8. 27.1. 24.8. FX. 58.5. 55.2. 56.8. 55.4. ... 25.3. 29.0. 24.3. 28.1. F2. 38.3. 41.6. 35.7. 37.3. F3. 25.3. -
Effects of Out of Vocabulary Words in Spoken Document Retrieval
mi.eng.cam.ac.uk/reports/full_html/woodland_sigir00.html/14 Aug 2000: ID. BASE. BRF. UBRF. 3k. 22.2. 24.4. 33.3. 7k. 33.8. 37.5. -
General Query Expansion Techniques for Spoken Document Retrieval
mi.eng.cam.ac.uk/reports/full_html/jourlin_esca99.html/2 Mar 2000: Our retrieval system was run on 7 different sets of automatically transcribed broadcast news texts with a WER varying from 24.8% to 66.2%. ... The overall system gave a WER of 24.8% which corresponded to a Processed Term Error Rate [11] (which more -
Spoken Document Retrieval for TREC-7 at Cambridge University
mi.eng.cam.ac.uk/reports/full_html/johnson_trec7.html/30 Mar 2000: This system gave a word error rate of 24.1% on the TREC-6 test data. ... map. stop. stem. CUHTK. 24.8. 25.0. 24.9. 22.8. 22.3. Dragon. 29.8. -
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. -
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 -
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 -
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. -
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%... -
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. -
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. -
THE CAMBRIDGE UNIVERSITY SPOKEN DOCUMENT RETRIEVAL SYSTEM S.E.…
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_icassp99.pdf8 Mar 2000: This system gave a word error rate of 24.1% on the TREC-6 test data and ran in about 50 times real time. ... Recogniser WER stop map stemIBM Baseline 50.0 47.5 47.2 44.3Sheffield 39.8 37.6 37.1 34.6HTK-1 28.6 24.9 24.7 -
The 1998 HTK Broadcast News Transcription System:Development and…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_darpa99.pdf8 Mar 2000: Y 14.2 8.0 15.4 20.3 16.5 14.0 16.6 24.6. ... ROVER fgintcat 4/Y1/N 13.8 7.8 15.1 20.1 15.8 13.6 16.6 24.1. -
EXPERIMENTS IN BROADCAST NEWS TRANSCRIPTION P.C. Woodland, T. Hain,…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_icassp98.pdf10 Apr 2000: M S TM 82.11 17.89 0.00N 15.27 84.22 0.51S 0.56 98.24 1.20T 0.00 1.19 98.81. ... 1F3 36.4 32.7 35.3 33.9F4 28.6 25.0 25.4 24.4F5 28.6 23.8 27.1 26.5FX 58.5 55.2 56.8 -
The 1997 HTK Broadcast News Transcription SystemP.C. Woodland, T. ...
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_darpa98.pdf8 Mar 2000: 36.5F4 24.2 25.1 23.1 21.3F5 25.7 24.1 25.9 23.0FX 57.2 53.7 57.1 50.4. ... 24.1 29.9ROVER BN2/3/gd ic 1/4 15.8 9.4 15.2 19.5 26.9 19.4 22.1 29.1. -
A Statistical Consistency Check for the SpaceCarving Algorithm. A. ...
mi.eng.cam.ac.uk/reports/svr-ftp/broadhurst_cipolla_bmvc2000.pdf25 Oct 2000: Figure 2: Resultsfrom the existing SpaceCarving algorithm using different thresholdsettings. The voxel array size was , and the thresholdswere 48,32,24,16(of 255)respectively. ... Figure 4: Resultsfrom the existing SpaceCarving algorithm using different -
The CUHTK-Entropic 10xRT Broadcast News Transcription SystemJ.J.…
mi.eng.cam.ac.uk/reports/svr-ftp/odell_darpa99.pdf8 Mar 2000: 22. 23. 24. 25. 26. 27. 28. 29. 30. 0 5 10 15 20 25. ... Comparing Table 4 with Table 3the advantage of including two passes can clearly be seen: onBNeval98 the error rate was reduced by 24% while the overallcomputation was increased by about a -
Effects of Out of Vocabulary Words in Spoken Document ...
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_sigir00.pdf10 May 2000: ID BASE BRF UBRF3k 22.2 24.4 33.37k 33.8 37.5 44.3. 14k 41.4 47.6 51.827k 43.0 49.7 53.855k 43.5 -
ITERATIVE UNSUPERVISED ADAPTATION USING MAXIMUMLIKELIHOOD LINEAR…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_icslp96.pdf17 Oct 2000: 704/c 26.3 15.570a/b 10.3 1.970f/d 18.8 7.670w/c 24.2 15.8. Table 1: Lattice error rates for several development test speakerswith ... a fg 14.24 —HMM-2 thresh. b fg 13.81 —HMM-2 thresh. c fg 13.71 6.68. -
A METHOD FOR DIRECT AUDIO SEARCH WITH APPLICATIONS TOINDEXING ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_icassp00.pdf19 Apr 2000: Of the 110 seconds worth of “news” rejected by the sys-tem with shorter windows, 24 seconds was due to an inter-view with Bill Clinton being re-broadcast, and the -
Segment Generation and Clustering in the HTKBroadcast News…
mi.eng.cam.ac.uk/reports/svr-ftp/hain_darpa98.pdf8 Mar 2000: M S T. M 82.11 17.89 0.00N 15.27 84.22 0.51S 0.56 98.24 1.20T 0.00 1.19 98.81. -
LARGE SCALE MMIE TRAINING FOR CONVERSATIONALTELEPHONE SPEECH…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_stw00.pdf5 Oct 2000: Lattices were generated on the training set using a bigramLM. The bigram 1-best hypotheses had a 24.6% word error rate(WER) and a Lattice WER (LWER) of 6.2%. -
The Applications of Uncalibrated Occlusion Junctions A.…
mi.eng.cam.ac.uk/reports/svr-ftp/broadhurst_cipolla_bmvc1999.pdf25 Oct 2000: 7] M.A. FischlerandR.C.Bolles.Randomsampleconsensus:A paradigmfor modelfitting with applicationsto imageanalysisandautomatedcartography. CACM, 24(6):381–395,June1981. [8] R.I. -
THE DEVELOPMENT OF THE1996 HTK BROADCAST NEWS TRANSCRIPTION SYSTEM ...
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_darpa97.pdf8 Mar 2000: Test Data Adaptation ClassesSubset None Global MultipleNM/FB 26.7 24.8 22.3BM/FB 41.2 32.8 31.3NM/RB 58.5 40.7 36.5Overall 36.4 ... HMM-2/1 trans fg 27.2 18.8 26.4 32.6 24.1 29.6 21.1 48.2HMM-2/2 trans fg 26.9 18.7 26.2 -
SPOKEN DOCUMENT RETRIEVAL FOR TREC-7 AT CAMBRIDGE UNIVERSITY S.E. ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_trec7.pdf8 Mar 2000: This system gave a word error rate of 24.1% on. the TREC-6 test data. ... 1 77.3 17.5 5.2 5.9 28.6HTK-2 80.8 14.6 4.6 4.9 24.1. -
GENERAL QUERY EXPANSION TECHNIQUESFOR SPOKEN DOCUMENT RETRIEVAL…
mi.eng.cam.ac.uk/reports/svr-ftp/jourlin_esca99.pdf10 Apr 2000: Theoverall system gave a WER of 24.8% which corre-sponded to a Processed Term Error Rate [11] (whichmore closely represents the error rate as seen by theretriever) of 32.1%. -
Recovery of Circular Motion from Profiles of Surfaces Paulo ...
mi.eng.cam.ac.uk/reports/svr-ftp/mendonca_iccv99ws.pdf1 Jun 2000: 36. 23. 35. 24. 34. 25. 33. 26. 32. 27. 31. ... 19. 3. 20. 2. 21. 1. 2223. 36. 24. 35. 25. -
Volume-based three-dimensionalmetamorphosis usingregion…
mi.eng.cam.ac.uk/reports/svr-ftp/treece_tr379.pdf26 Apr 2000: Althoughvolume graphics (the storage and display of volumetric data as opposed to polygonal surfaces)has advanced considerably over the last decade [14, 24], most surfaces are still defined aspolygonal models, and ... the skeleton representation [2]and -
3D ultrasound examination of large organs G.M. Treece, R.W. ...
mi.eng.cam.ac.uk/reports/svr-ftp/treece_tr367.pdf12 May 2000: There are several techniques which can successfully generate this voxelarray from single sweeps [24]. ... Figure 1(a), forinstance, shows two sweeps from a liver examination which have been interpolated using thevoxel nearest neighbour [24] interpolation. -
SPOKEN DOCUMENT RETRIEVAL FOR TREC-8 AT CAMBRIDGE UNIVERSITY S.E. ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_trec8.pdf10 Apr 2000: an Average Precision (AveP) of 55.88 obtained on referencetranscriptions, 55.08 on our own transcriptions (24.8% WER)and 44.15 on transcriptions from DERA [17] (61.5% WER) onthe ... high 39.97% 0.24% 54.65% 1.54%Slide low 59.41% 0.17% 68.35% 1.38%L=10s -
Audio Indexing and Retrieval of Complete Broadcast News Shows ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_riao00.pdf10 Apr 2000: SPI Post RS NRS NS #Dup AveP R-PY B 96.0 39.39 27.42 752913 - -N B 95.8 37.52 24.92 698461 - -Y A 78.3 ... InProc. TREC-7, NIST SP 500-242, pages 1–24, Gaithersburg, MD. Introduction. Description of Task and Data. -
Reducing Word Error Rates of Found Speech -XPERT Tool ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_tr330.pdf10 Apr 2000: Corr Ins Sub Del WERROBERT VITO 166 19 56 8 36%RON HOFSTETTER 27 4 48 22 76%BUFFALO TIGER 14 3 18 2 67%FX 188 24 115 32 50% ... 24 Files Required for Processing. ;;;; more comments about the format/condition categories;;a960523 1 Ted_Koppel 399.063 -
Pronunciation modeling by sharing Gaussians
mi.eng.cam.ac.uk/reports/svr-ftp/nock_csl00.pdf31 Jul 2000: 0885–2308/00/020137 24 $35.00/0 c 2000 Academic Press. 138 M. Saraçlaret al. -
Submitted in partial requirement for the MPhil in Computer ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_mthesis.pdf10 Apr 2000: 39.77Condition Match(%) 54.19 17.24 19.70 21.18 25.12 11.82 24.63 42.86 41.38Total Match(%) 58.12 1.88 2.50 2.50 ... 45 35.96 39.90 49.75 53.20 53.20 29.06 27.09 53.69Total Match(%) 20.00 24.38 25.00 56.25 58.12 51.25
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.