Search
Search Funnelback University
- Refined by:
- Date: 2018
Did you mean economiespast |u:mi.eng.cam.ac.uk?
1 -
50 of
432
search results for Economics test |u:mi.eng.cam.ac.uk
where 2
match all words and 430
match some words.
Fully-matching results
-
Evaluation of Statistical POMDP-basedDialogue Systems in Noisy…
mi.eng.cam.ac.uk/~sjy/papers/ybgh14.pdf20 Feb 2018: Contrasts marked are statisticallysignificant (p < 0.05) using a Kruskal-Wallis rank sum test. ... Test System Num Objective Success Rate Perceived Average WERDialogs Partial Full Success Rate Turns. -
Neural Belief Tracker: Data-Driven Dialogue State Tracking Nikola…
mi.eng.cam.ac.uk/~sjy/papers/mowt17.pdf20 Feb 2018: The training data con-tains 2207 dialogues and the test set consistsof 1117 dialogues. ... For goals, the gains are always statis-tically significant (paired t-test, p < 0.05). Results that match 1 of 2 words
-
Simplifying very deep convolutional neural network architectures for…
mi.eng.cam.ac.uk/UKSpeech2017/posters/j_rownicka.pdf3 Jul 2018: MGB-3 dev set (5 h). MGB-1 test set (19 h). Results: Aurora4. ... contributed most to the performance gains in our experiments, especially fornoisy test data. -
Impact of ASR Performance on Free Speaking Language Assessment ...
mi.eng.cam.ac.uk/~ar527/knill_is2018.pdf15 Jun 2018: This form of test allows the spoken language pro-ficiency of a non-native speaker of English to be assessed morefully than read aloud tests. ... The BULATS test comprises 5 sections:A. short responses; B. read aloud sentences; C-E. -
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2005-MVA-Conde.pd…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2005-MVA-Conde.pdf13 Mar 2018: 418. 2. DATA ACQUISITION SETUP In order to develop the tests here exposed, a set of 3D facial data have been acquired. ... The processing time was shorter than ten seconds even for the worst situation met during test step. -
Towards Automatic Assessment of Spontaneous Spoken English Y.…
mi.eng.cam.ac.uk/~mjfg/ALTA/publications/ALTA_SpComm2017.pdf12 Sep 2018: computed over all the test sectionswhere the candidate is required to produce spontaneousspeech. ... xN}, what is the best estimate of thevalue of the function at test point x. -
Automatic speech recognition formedia monitoring in SUMMA Peter Bell, …
mi.eng.cam.ac.uk/UKSpeech2017/posters/p_bell.pdf3 Jul 2018: Current results on SUMMA test sets. Language Word Error Rate† (%)English (MGB Challenge) 26.1Arabic (MGB Challenge) 14.7German 34.6Russian 40.0. ... Work is ongoing to transcribe test sets for the remaining languages. -
Use of Graphemic Lexicons for Spoken Language Assessment K.M. ...
mi.eng.cam.ac.uk/~ar527/knill_is2017.pdf15 Jun 2018: Testing Service (BULATS). The BULATS speaking test has fivesections, all related to business scenarios [19]. ... Test Set Ph/Gr Vit CN. GujaratiPh 34.3 33.7Gr 33.3 32.5. Ph Gr - 31.6. -
91_20090306_170604
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2009-MVA-Mavaddat.pdf13 Mar 2018: The model can now be used to classify test imagepatches as text or non-text. ... The test patches were ex-tracted in the same manner as the training patches. -
sigdial11_sdc10-Feb27-V2
mi.eng.cam.ac.uk/~sjy/papers/bbch11.pdf20 Feb 2018: This paper presents the results of the live tests, and compares them with the control test results. ... Some interesting differences between the sys-tems are evident in the live tests. -
RTSC MAGPHASE VOCODER: MAGNITUDE ANDPHASE ANALYSIS/SYNTHESIS FOR…
mi.eng.cam.ac.uk/UKSpeech2017/posters/f_espic.pdf19 Jan 2018: evaluated by 30 native En-glish speakers using a MUSHRA-like test. ... Eachsubject evaluated 36 different sentences (18male, 18 female). The systems under test were:. • -
An attention based model for off-topic spontaneous spoken response ...
mi.eng.cam.ac.uk/~ar527/malinin_slate2017.pdf15 Jun 2018: Data from the Business Language Testing Service(BULATS) English tests was used for training and test. ... To avoid a data mismatch,the recognition hypothesis was used both in training and test. -
ADAPTATION OF AN EXPRESSIVE SINGLE SPEAKER DEEP NEURAL NETWORKSPEECH…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2018-ICASSP-speaker-adaptation.pdf3 May 2018: Test subjectswere asked to assess the quality of the speech on a 1-5 scale. ... 10 test subjectswere used. Models A and B are compared and models A and C arecompared. -
intspch2007_inanoglu_young.dvi
mi.eng.cam.ac.uk/~sjy/papers/inyo07.pdf20 Feb 2018: The relevant contextual factors were cho-sen as a result of informal perceptual tests. ... 6. EvaluationA perceptual listening test was conducted to evaluate the com-bined conversions. -
paper.dvi
mi.eng.cam.ac.uk/~ar527/ragni_is2018a.pdf15 Jun 2018: The. Table 3:Test audio data summary. Id Set Band Type Dur (hrs). ... Acero, “Estimating speech recogni-tion error rate without acoustic test data,” inEurospeech, 2003. -
Intonation Modelling and Adaptation for Emotional Prosody Generation…
mi.eng.cam.ac.uk/~sjy/papers/inyo0520 Feb 2018: Adaptatation to a very small amountof sad speech data also resulted in considerably sadder prosody, as confirmed bypreference tests. ... A t-test(p<0.05) on the two samples confirmed that the samples are not statisticallydistinguishable. -
nips7.dvi
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2005-ANIPS-Williams-VIC-algorithm.pdf13 Mar 2018: This is restrictive in practicein that test data may contain distortions that take it outside the strict ambit of the trainingpositives. ... This can be computed in terms of likelihoods. (1)so then the test becomes (2)where. -
WeilhammerStuttleYoungICSLP2006.dvi
mi.eng.cam.ac.uk/~sjy/papers/wesy06.pdf20 Feb 2018: Thedata was divided into a test set and a training set (see table 1). ... PPL (held out)WER (test). k sentences. WER. (%) /. PPL. Language Modelling Toolkit [12]. -
IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B:…
mi.eng.cam.ac.uk/~cipolla/publications/article/2006-SMC-localisation.pdf13 Mar 2018: Using the later index,Test-C tests Sequence-I, Test-D tests Sequence-II. The correctratios of the coarse localization are shown in Fig. ... Fig. 9. Layout of the outdoor environment in a campus. Test-E tests Sequence-III. -
poyosp08
mi.eng.cam.ac.uk/~sjy/papers/dpyo08.pdf20 Feb 2018: Objective evaluation. In order to test the performance of the different repair systems,. ... T - O 0.66 0.20 0.14. Table 8: Preference test results. -
Tracking Using Online Feature Selectionand a Local Generative Model…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2007-BMVC-Woodley.pdf13 Mar 2018: We perform the adapted online feature selection algorithm (see Alg. 1) on a numberof test sequences. ... We take a single test image, and create a test sequence by adding fixed size, randomlypositioned black squares to simulate occlusion. -
A DATA-DRIVEN SPOKEN LANGUAGE UNDERSTANDING SYSTEM Yulan He Steve ...
mi.eng.cam.ac.uk/~sjy/papers/heyo03b.pdf20 Feb 2018: class-based trigram 4.8 3.4. Table 1. Test results for the speech recognizer (%WER). ... Forthe NL test, the semantic parser used as input the reference tran-scriptions instead of the recognized output. -
Learning Discriminative Canonical Correlationsfor Object Recognition…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2006-ECCV-Kim-imagesets.pdf13 Mar 2018: We used 18randomly selected training/test combinations for reporting identification rates. Comparative Methods. ... 0.9. 1. Dimension. Iden. tific. atio. n ra. te. Effect of the dimension on the test set. -
JOINT MODELLING OF VOICING LABEL AND CONTINUOUS F0 FOR ...
mi.eng.cam.ac.uk/~sjy/papers/yuyo11a.pdf20 Feb 2018: For the test material 30 sentences from a tourist information en-quiry application were used. ... JVF IVF. Fig. 2. Comparison between CF-IVF and CF-JVF on a forced choicepreference test. -
The Linear Transformation of LF Glottal Waveforms for Voice ...
mi.eng.cam.ac.uk/~sjy/papers/poyo08b20 Feb 2018: Figure 6: Results of the ABX test. between each source and target speaker pair. ... perc. enta. ge. PSHM. JEAS. MM MF FM FF. PSHMJEAS. Figure 7: Results of the quality comparison test. -
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2005-MVA-…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2005-MVA-Conde.pdf13 Mar 2018: 418. 2. DATA ACQUISITION SETUP In order to develop the tests here exposed, a set of 3D facial data have been acquired. ... The processing time was shorter than ten seconds even for the worst situation met during test step. -
stenger_imavis06.dvi
mi.eng.cam.ac.uk/~cipolla/publications/article/2008-IVC-Stenger.pdf13 Mar 2018: The parameters for both methods are setby testing the classification performance on a test setof 5000 images. ... In a first approach,the edge and colour cost terms are computed for a numberof test images. -
A New Look at Filtering Techniques for Illumination Invariance ...
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2006-AFGR-Arandjelovic-filtering.pdf13 Mar 2018: State-of-the-art commercial system FaceIt by Identix[12] (the best performing software in the most recentFace Recognition Vendor Test [13]),. • ... KLD) [14]. In all tests, both training data for each person in the gallery,as well as test data, -
91_20090306_170604
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2009-MVA-Mavaddat.pdf13 Mar 2018: The model can now be used to classify test imagepatches as text or non-text. ... The test patches were ex-tracted in the same manner as the training patches. -
Incremental Learning of Locally OrthogonalSubspaces for Set-based…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2006-BMCV-Kim-incremental.pdf13 Mar 2018: Iden. tific. atio. n ra. te. Effect of the dimension on the test set. ... Anindependent illumination set with both training and test sets was exploited for the val-idation. -
ADAPTATION OF AN EXPRESSIVE SINGLE SPEAKER DEEP NEURAL NETWORKSPEECH…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2018-ICASSP-speaker-adaptation.pdf3 May 2018: Test subjectswere asked to assess the quality of the speech on a 1-5 scale. ... 10 test subjectswere used. Models A and B are compared and models A and C arecompared. -
DEEP-CARVING: Discovering Visual Attributes by Carving Deep Neural…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2015-CVPR-Shankar.pdf13 Mar 2018: M}. For a test image xt, the task is to predictyt A, i.e. ... The vali-dation set and the test set contain 2104 and 2967 imagesrespectively. -
Robust Instance Recognition in Presence ofOcclusion and Clutter Ujwal …
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2014-ECCV-3D-recognition.pdf13 Mar 2018: We capture six test scenes with the same five objects. Eachtest scene has 400 500 frames containing multiple objects with different back-grounds/clutter and poses.Scenario 4: This scenario tests ... Recall. Pre. cis. ion. LineModSupp. SIterative(Edge). -
Learning Motion Categories using both Semantic and Structural…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2007-CVPR-Wongsf-learning.pdf13 Mar 2018: Quantitative test was done on unsegmented KTH datasetusing the classifiers learnt in the previous experiment. ... In test set-up, we used unsegmentedKTH data for incremental training (i.e. -
Exploiting Sentence and Context Representations in Deep Neural…
mi.eng.cam.ac.uk/~sjy/papers/rgms16.pdf20 Feb 2018: Table 2 shows the results on the test sets. Consequently, when evaluating on the DSTC2 test set, awindow of 4 (w4), performs slightly better than other window sizes and better than ... On the In-car testset, a context window of 4 outperforms all the -
0000010020030040050060070080090100110120130140150160170180190200210220…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2017-BMVC-bayesian-SegNet.pdf13 Mar 2018: This is achieved by sampling the network with randomly droppedout units at test time. ... Table 3: Pascal VOC12 [9] test results evaluated from the online evaluation server. -
Chapter 1 Achieving Illumination Invariance using Image Filters…
mi.eng.cam.ac.uk/~cipolla/publications/contributionToEditedBook/2007-FR-chapter1.pdf13 Mar 2018: 0. 0.1. 0.2. 0.3. 0.4. 0.5. Test index. Rel. ativ. e re. ... The tests are shown in the order of increasing raw data performance foreasier visualization. -
C:/SFWDoc/Academic/Publications/2005/BMVC_2005/FinalPaper/bmvc_05_sfwo…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2005-BMVC-Wongsf-realtime.pdf13 Mar 2018: cluttered background, and background with skin colour). The overallaccuracyon 1025 test cases is 89.7%. ... Thepercentage of test cases that cannot be mapped into any classis 20.3%. -
TPAMI-0554-0706-2 1..14
mi.eng.cam.ac.uk/~cipolla/publications/article/2007-PAMI-Kim.pdf13 Mar 2018: We used 18 randomlyselected training/test combinations of the sequences forreporting identification rates. ... The test recognition rates changed byless than 1 percent for all of the different trials of randompartitioning. -
Gesture Recognition Under Small Sample Size Tae-Kyun Kim1 and ...
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2007-ACCV-Kim.pdf13 Mar 2018: High dimensional inputspace and a small training set often cause over-fitting of classifiers to the training data and poorgeneralization to new test data. ... 3. Nevertheless, the twointersection sets of the train and test sets are stillplaced in the -
nips7.dvi
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2005-ANIPS-Williams-VIC-algorithm.pdf13 Mar 2018: This is restrictive in practicein that test data may contain distortions that take it outside the strict ambit of the trainingpositives. ... This can be computed in terms of likelihoods. (1)so then the test becomes (2)where. -
Learning to Track with Multiple Observers Björn StengerComputer…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2009-CVPR-hand-tracking.pdf13 Mar 2018: The running of tests consisting of all possible combina-tions of all trackers on all test sequences would take a pro-hibitive amount of time to complete. ... In order to test the validity of such a setup, weperformed tests using the complete tracking -
Latent Intention Dialogue Models Tsung-Hsien Wen 1 * Yishu ...
mi.eng.cam.ac.uk/~sjy/papers/wmby17.pdf20 Feb 2018: During test-ing, we greedily selected the most probable intention andapplied beam search with the beamwidth set to 10 when de-coding the response. ... The significance test is based on atwo-tailed student-t test, between NDM and LIDMs. -
DISTRIBUTED DIALOGUE POLICIES FOR MULTI-DOMAIN STATISTICAL…
mi.eng.cam.ac.uk/~sjy/papers/gkty15.pdf20 Feb 2018: Bold values are statis-tically significant compared to non-bold values in the same groupusing an unpaired t-test with p < 0.01. ... The difference between bold valuesand non-bold values is statistically significant using an unpaired t-test where p < 0.02. -
SegNet: A Deep Convolutional Encoder-Decoder Architecture for…
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2015-arxiv-SegNet.pdf13 Mar 2018: We test the performance of SegNet on outdoorRGB scenes from CamVid, KITTI and indoor scenes fromthe NYU dataset. ... Features based on appearance[32], SfM and appearance [2, 36, 20] have been explored forthe CamVid test. -
Modelling Uncertainty in Deep Learning for Camera Relocalization Alex …
mi.eng.cam.ac.uk/~cipolla/publications/inproceedings/2016-ICRA-pose-uncertainty.pdf13 Mar 2018: This is achieved by sampling the network withrandomly dropped out connections at test time. ... At test time we perform inference byaveraging stochastic samples from the dropout network. -
Conditional Generation and Snapshot Learning inNeural Dialogue…
mi.eng.cam.ac.uk/~sjy/papers/wgmr16a.pdf20 Feb 2018: 2016a). Statisticalsignificance was computed using two-tailed Wilcoxon Signed-Rank Test ( p <0.05) to compare models w/and w/o snapshot learning. ... 0.540 0.559 0.459. Table 2: Average activation of gates on test set. -
Using Wizard-of-Oz simulations to bootstrap…
mi.eng.cam.ac.uk/~sjy/papers/wiyo03.pdf20 Feb 2018: Sections 3 and 4 detail a method for addressing these issues, and the procedure used to test the method, respectively. -
Tracking Using Online Feature Selectionand a Local Generative Model…
mi.eng.cam.ac.uk/~cipolla/archive/Publications/inproceedings/2007-BMVC-Woodley.pdf13 Mar 2018: We perform the adapted online feature selection algorithm (see Alg. 1) on a numberof test sequences. ... We take a single test image, and create a test sequence by adding fixed size, randomlypositioned black squares to simulate occlusion. -
acl2010.dvi
mi.eng.cam.ac.uk/~sjy/papers/gjkm10.pdf20 Feb 2018: functionsfrom Table 1.The intention was, not only to test which algo-rithm yields the best policy performance, but alsoto examine the speed of convergence to the opti-mal policy.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.