Search
Search Funnelback University
51 -
60 of
1,000
search results for katalk:za31 24 / / / / / |u:mi.eng.cam.ac.uk
where 0
match all words and 1,000
match some words.
Results that match 1 of 2 words
-
More Robust Schema-Guided Dialogue State Tracking via…
mi.eng.cam.ac.uk/~wjb31/eacl_2023_CR.pdf1 Mar 2023: lightweight data augmentation for lowresource slot filling and intent classification. In Pro-ceedings of the 34th Pacific Asia Conference on Lan-guage, Information and Computation, PACLIC 2020,Hanoi, Vietnam, October -
Applying Deep Learning in Non-native Spoken English Assessment
mi.eng.cam.ac.uk/~mjfg/ALTA/presentations/APSIPA2019_Knill.pdf21 Feb 2022: 1.0 indicates within one CEFR grade-level. 24/45. Assessment System Performance. • ... 1.0 indicates within one CEFR grade-level. 24/45. Performance Analysis. 25/45. -
EFFECTS OF THE USER MODEL ON SIMULATION-BASEDLEARNING OF DIALOGUE ...
mi.eng.cam.ac.uk/~sjy/papers/swsy05.pdf20 Feb 2018: The COMMUNICATOR systems in contrast onlyrequest between 24% and 43% of the unknown slots in each state. -
Structured Discriminative Models Using Deep Neural-Network Features
mi.eng.cam.ac.uk/~mjfg/asru15-vanDalen.pdf11 Mar 2016: MPE— 7.15 11.06 14.37 24.54 16.79CML 6.95 11.00 14.29 24.39 16.68large-margin 7.02 10.92 14.16 24.28 ... Therefore the systems use graphemic lex-ica generated using an approach which is applicable to all Unicodecharacters [24]. -
CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT DISCRIMINATIVE…
mi.eng.cam.ac.uk/~mjfg/gales_tr605.pdf13 Aug 2008: In common with other work in this. 5. area [9, 24], G is approximated by the diagonalised empirical covariance matrix of the trainingdata. ... 00 25.48 21.73 25.95 24.46 21.64 26.05 24.51 22.56. -
AUTOMATIC COMPLEXITY CONTROL FOR HLDA SYSTEMS X. Liu, M. ...
mi.eng.cam.ac.uk/reports/svr-ftp/liu_icassp2003.pdf19 Sep 2003: Fig. 1. Test set word error rate for all possible models, with thestandard front-end 12, 16 and 24 component performance. ... The best perfor-mance, 36.8%, was obtained using 24 components per state and anHLDA projection from 52 dimensions to 38 -
Towards Learning Orientated Assessment for Non-native Learner Spoken…
mi.eng.cam.ac.uk/~kmk/presentations/ALTA_Sheffield_20190306.pdf8 Mar 2019: 300 300. 25.5. 400 24.5. 400 24.4. ASR on Non-native Speech (2). • ... Thai dh d 7.24 oh aa 5.21. 30. • Top 2 recurrent substitution errors for speakers in each L1. -
Towards Learning Orientated Assessment for Non-native Learner Spoken…
mi.eng.cam.ac.uk/~mjfg/ALTA/presentations/ALTA_Sheffield_20190306.pdf21 Feb 2022: 300 300. 25.5. 400 24.5. 400 24.4. ASR on Non-native Speech (2). • ... Thai dh d 7.24 oh aa 5.21. 30. • Top 2 recurrent substitution errors for speakers in each L1. -
SYSTEM COMBINATION AND SCORE NORMALIZATION FOR SPOKEN TERM DETECTION
mi.eng.cam.ac.uk/~mjfg/ICASSP13_ibm1.pdf13 Jun 2013: Ney LM with optimized discounting parameters [24] usinga modified version of the RWTH open source decoder [25]; and (6)DBN, a deep belief network hybrid model [26, 27] with discrimi-native ... Ney, “Posterior-scaled mpe: Novel discriminative -
eps.dis.dur.testa.eps
mi.eng.cam.ac.uk/~mjfg/gales_ASRU09.pdf14 Sep 2010: Using 17 pairs, about 24% of thetotal number of pairs, 92% of the WER improvement usingthe 1-v-1 system over the VTS baseline was achieved.
Refine your results
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.