Search
Search Funnelback University
31 -
40 of
1,000
search results for katalk:PC53 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
-
A HIGH-PERFORMANCE CANTONESE KEYWORD SEARCH SYSTEM
mi.eng.cam.ac.uk/~mjfg/ICASSP13_ibm2.pdf13 Jun 2013: with 24% speaking the Central Guangdong, 20%the Northern Pearl River Delta, 19% the Southern Pearl River Delta,19% the Guangxi and Western Guangdong, and 18% the NorthernGuangdong dialects. ... System combination is performed using an -
Addressing Objects and Their Relations:The Conversational Entity…
mi.eng.cam.ac.uk/~sjy/papers/ubcr18.pdf3 Jul 2018: shows that the CEDM learns to address a relationin up to 24.5% of all dialogues for r = 1.0. ... Computer Speech & Lan-guage, 24(2):150–174. Steve J. Young, Milica Gašić, Blaise Thomson, and Ja-son D. -
The Hidden Information State model: A practical framework for…
mi.eng.cam.ac.uk/~sjy/papers/ygkm10.pdf20 Feb 2018: S. Young et al. / Computer Speech and Language 24 (2010) 150–174 151. ... 152 S. Young et al. / Computer Speech and Language 24 (2010) 150–174. -
crosseval_diff-reward2b.ps
mi.eng.cam.ac.uk/~sjy/papers/kgjm10.pdf20 Feb 2018: Yu. 2009. The Hidden InformationState model: a practical framework for POMDPbased spoken dialogue management.ComputerSpeech and Language, 24(2):150–174. -
EFFICIENT LATTICE RESCORING USINGRECURRENT NEURAL NETWORK LANGUAGE…
mi.eng.cam.ac.uk/~mjfg/xl207_ICASSP14a.pdf28 Apr 2014: Instead, previous research has beenfocused on using N-best list rescoring for RNNLM performanceevaluation [13, 14, 26, 27, 24]. ... 21, no. 3, pp. 492–518,2007. [24] Y. Si, Q. Zhang, T. -
Optimisation for POMDP-based Spoken Dialogue Systems M. Gašić, F.…
mi.eng.cam.ac.uk/~sjy/papers/gjty12.pdf20 Feb 2018: To obtain a closed formsolution of (24), the policy π must be differentiable with respect to θ. ... 10. To lower the variance of the estimate of the gradient, a constant baseline, B, can beintroduced into (24) without introducing any bias [22]. -
DISCRIMINATIVE SPOKEN LANGUAGE UNDERSTANDINGUSING WORD CONFUSION…
mi.eng.cam.ac.uk/~sjy/papers/hgtt12.pdf20 Feb 2018: 24, no. 4, Oct. 2010. [16] S. J. Young, G. Evermann, M. -
Phrase-based Statistical Language Generation usingGraphical Models…
mi.eng.cam.ac.uk/~sjy/papers/mgjk10.pdf20 Feb 2018: Com-puter Speech & Language, 24(4):562–588, 2010. Y. Tokuda, T. Yoshimura, T. ... Computer Speech and Language,24(2):150–174, 2010. -
From Discontinuous To Continuous F0 Modelling In HMM-based…
mi.eng.cam.ac.uk/~sjy/papers/yuty10.pdf20 Feb 2018: The feature set includes 24 spectralcoefficients, log F0 and 5 aperiodic component features. -
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, JANUARY…
mi.eng.cam.ac.uk/~sjy/papers/gayo14.pdf20 Feb 2018: An advantage of this sparsification approach is that itenables non-positive definite kernel functions to be used in theapproximation, for example see [24]. ... It has already beenshown that active learning has the potential to lead to fasterlearning [24]
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.