Search
Search Funnelback University
- Refined by:
- Date: 2000
Did you mean economiespast |u:mi.eng.cam.ac.uk?
21 -
40 of
48
search results for Economics test |u:mi.eng.cam.ac.uk
where 0
match all words and 48
match some words.
Results that match 1 of 2 words
-
The CUHTK-Entropic 10xRT Broadcast News Transcription SystemJ.J.…
mi.eng.cam.ac.uk/reports/svr-ftp/odell_darpa99.pdf8 Mar 2000: In tests the fastercache led to 6-8% faster decoder operation on a Xeon than onthe equivalent Pentium II. ... Further tests under different operating systems indicated that. compiler efficiency was also an important issue. -
THE DEVELOPMENT OF THE1996 HTK BROADCAST NEWS TRANSCRIPTION SYSTEM ...
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_darpa97.pdf8 Mar 2000: approach, and two sets of HMMs were adapted.The test data for F2 was also automatically labelled as narrow. ... 1995 Hub-4 “Dry-Run” Broadcast Materials Bench-mark Tests. Proc. DARPA Speech Recognition Workshop, Har-riman, New York. -
THE CAMBRIDGE UNIVERSITY SPOKEN DOCUMENT RETRIEVAL SYSTEM S.E.…
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_icassp99.pdf8 Mar 2000: Two versions of the HTK system were used in the experimentson TREC-6 SDR test data. ... This system gave a word error rate of 24.1% on the TREC-6 test data and ran in about 50 times real time. -
Global Optimisation of Neural Network Models Via Sequential…
mi.eng.cam.ac.uk/reports/full_html/freitas_icslp98.html/8 Mar 2000: Figure 3: Network prediction on training and test data. Actual output[. -
Audio Indexing and Retrieval of Complete Broadcast News Shows
mi.eng.cam.ac.uk/reports/full_html/johnson_riao00.html/19 Apr 2000: The windows were compared to a library of windows stored from previous shows from the broadcaster (the broadcast history) [In theory all the data in the test collection could be used ... The amount of commercial rejection with the VOA data is low, due -
THE CU-HTK MARCH 2000 HUB5E TRANSCRIPTION SYSTEMT. Hain, P.C. ...
mi.eng.cam.ac.uk/reports/svr-ftp/hain_stw00.pdf5 Oct 2000: While MMIE is very effective at reducing training set error a keyissue is generalisation to test data. ... On other test setsimprovements greater than 1% absolute have also been obtained and. -
Segment Generation and Clustering in the HTKBroadcast News…
mi.eng.cam.ac.uk/reports/svr-ftp/hain_darpa98.pdf8 Mar 2000: 9 26 142. Table 1: Training and test material available in broadcast news (min-utes) for music (M) background speaker (BGS), other background(BGO), music and speech (MS), narrow-band (T) ... The test set is split into shows available bothin training and -
The 1997 HTK Broadcast News Transcription SystemP.C. Woodland, T. ...
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_darpa98.pdf8 Mar 2000: news development test data andjust 15.8% on the 1997 evaluation test set. ... The OOV rate on both these test sets using the filteredtranscriptions was about 0.5%. -
Pronunciation modeling by sharing Gaussians
mi.eng.cam.ac.uk/reports/svr-ftp/nock_csl00.pdf31 Jul 2000: Pronunciation modeling by sharing Gaussians 141. TABLE I. WER degradation with speaking style on theMULTI-REG test set. ... Steps (6), (3), (4) and (5) arethen carried out in that order to estimate and test a matched pronunciation model. -
LARGE SCALE DISCRIMINATIVE TRAINING FORSPEECH RECOGNITION P.C.…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_asr00.pdf6 Nov 2000: ing in general) is the generalisation performance i.e. the dif-ference between training set and test set accuracy. ... Baseline Models and Hub5 Training/Test DataThree different training sets and three different test sets. -
PII: S0167-6393(99)00037-0
mi.eng.cam.ac.uk/reports/svr-ftp/nock_specom99.pdf31 Jul 2000: nemea. Training data Average log2-prob (eciency). ICSI-test TIMIT-test. TIMIT 0.76! 0.60. ... derivation of the training transcrip-tions, and the hand-labelling of the test set. -
EXPERIMENTS IN BROADCAST NEWS TRANSCRIPTION P.C. Woodland, T. Hain,…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_icassp98.pdf10 Apr 2000: spontaneous non-native). Table 1: Broadcast news focus conditions. For development test purposes, data broadcast in July 1996from six shows was used. ... Overall 19.0 21.0. Table 9: % Word error rates on the Marketplace dev-test show forautomatic and -
Class-based language model adaptation using mixtures ofword-class…
mi.eng.cam.ac.uk/reports/svr-ftp/moore_icslp00.pdf2 Nov 2000: 4 ExperimentsThe full HUB-4 1997 evaluation test set was used to as-sess language model performance.1 Although the trainingtext described in section 3 was chosen to try and matchthe ... Treating this asthe baseline result to improve upon, statistical -
A Statistical Consistency Check for the SpaceCarving Algorithm. A. ...
mi.eng.cam.ac.uk/reports/svr-ftp/broadhurst_cipolla_bmvc2000.pdf25 Oct 2000: The test sequence(seefigure 8 ) consistsof a hollow unit cubewith textured imageson the back threefaces.This configurationwaschosenbecauseit hasa largehollow volumethathasto becarvedaway, and the exterior boundarygives no information aboutthe -
SPOKEN DOCUMENT RETRIEVAL FOR TREC-7 AT CAMBRIDGE UNIVERSITY S.E. ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_trec7.pdf8 Mar 2000: Development work on the TREC-6 test corpus was done using twoHTK based systems. ... But more importantly, the test data is too small for reliable andinformative inference. -
SPOKEN DOCUMENT RETRIEVAL FOR TREC-8 AT CAMBRIDGE UNIVERSITY S.E. ...
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_trec8.pdf10 Apr 2000: Preprocess & apply SPI to the test collection to giveIt2. Preprocess & apply SPI to parallel collection to giveIp3. ... This contains the TREC-8 SDR test collectionperiod (Feb 1st to June 30th 1998). -
The 1998 HTK Broadcast News Transcription System:Development and…
mi.eng.cam.ac.uk/reports/svr-ftp/woodland_darpa99.pdf8 Mar 2000: During system development theBNeval97 test set was used. 4.1. Increased Acoustic Training Data. ... All these sources ex-cluded data from the designated test epochs. This corpus wasdenoted LMtrain98. -
POSTERIOR PROBABILITY DECODING, CONFIDENCEESTIMATION AND SYSTEM…
mi.eng.cam.ac.uk/reports/svr-ftp/evermann_stw00.pdf5 Oct 2000: It canbe seen that for the eval00 test set the unmapped posteriors performmuch better than for the eval98 set. ... Table 4: System Combination Results. The improvement over the single best system achieved byROVER are rather disappointing especially on -
SPEAKER CLUSTERING USING DIRECT MAXIMISATION OFTHE MLLR-ADAPTED…
mi.eng.cam.ac.uk/reports/svr-ftp/johnson_icslp98.pdf10 Apr 2000: 1. INTRODUCTION. For speech transcription problems with widely varyingspeaker, channel and background conditions, such asbroadcast news transcription, it is beneficial to include un-supervised test-data adaptation to individual speakers anddata -
GENERAL QUERY EXPANSION TECHNIQUESFOR SPOKEN DOCUMENT RETRIEVAL…
mi.eng.cam.ac.uk/reports/svr-ftp/jourlin_esca99.pdf10 Apr 2000: The output of the first pass is used alongwith a top-down covariance-based segment clusteringalgorithm [10] to group segments within each show toperform unsupervised test-set adaptation using maxi-mum ... 5. RESULTS. The five systems described in section4
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
- dylan maxwell |u:www.statslab.cam.ac.uk (4) · moments ago
Recent searches
Your search history is empty.