Search

20 Feb 2018: Trial # users average # calls median # callsAMT 140 6.5 2Cambridge 17 24.4 20. ... vol. 24, no. 2, pp.150–174, 2010. [7] Amazon, “Amazon Mechanical Turk,” 2011.

3 Jul 2018: 24,000 fishermen a year. Mostly in storms. And not every country keeps accurate records.

4 Nov 2018: 23] L. Breiman. Bagging predictors. Machine learning,24(2):123–140, 1996. [24] O. Siohan, B. ... IEEE/ACM Transactions on Audio, Speech,and Language Processing, 24(8):1438–1449, 2016. Introduction. Graphemic English systems.

3 Jul 2018: training set of Aurora4. Model A B C D AVGDNN/clntr 2.71 43.00 24.06 58.66 45.48VDCNN-max-4FC/clntr 2.32 35.99 21.20 ... 24, no. 12, pp. 2263-2276, Dec. 2016. Contact: j.m.rownicka@sms.ed.ac.uk.

20 Feb 2018: error rate of 33.2 %, and for the first and secondorder derivatives the error rates of the classifiers are 33.1 %and 24.2 %, respectively. ... 24.8 42.4par 22.7 13.1 21.7 32.4 32.7 25.2 27.4 45.1.

15 Jun 2018: Sig-nificant WER improvements were observed after interpolatingwith the n-gram LM for n-best rescoring – a common practicefor speech recognition [8, 24, 25]. ... 24] S. Kombrink, T. Mikolov, M. Karafiát, and L. Burget, “Recurrentneural network

20 Feb 2018: Per-turn. WER. Per-dialog WER. None 2 6 24 83 % 0 % 0 % Low 4 12 48 83 % 32 % 28 % Med 4 12 48 77 % 46 % 41 % Hi 2 6 24 ... Dataset. Metrics (task & user sat). R2 Significant predictors. ALL User-S 52 % 1.03 Task ALL User-C 60 % 5.29 Task – 1.54

15 Jun 2018: LM rescoredev eval. Vit CN Vit CNng4 - 23.8 23.5 24.2 23.9. ... LM #succ words dev evalng4 23.8 24.2. uni-rnn - 21.7 22.1.

20 Feb 2018: Computer Speech and Language,24(4):562–588. O Tsimhoni, D Smith, and P Green. ... Computer Speech andLanguage, 24(2):150–174.

15 Jun 2018: The stage onesystem used an HTK [24] configuration that had been previ-ously employed for all Babel tasks [25, 26], multi-genre En-glish broadcast transcription [27] and many others. ... 25, no. 3, pp. 373–377, 2017. [24] S. J. Young, G.

20 Feb 2018: wwpos 24.52 11.29 18.47wspos 11.33 4.91 3.31wpof s 1.13 4.82 8.82wppof s 24.27 6.49 10.54wonset 15.08 0.33 ... 47.3% 52.7%. 75.3% 24.7%. Figure 3: Categorical quality ratings for spectral conversion duration conversion HMM-based contour generation.

15 Jun 2018: In [24] phonetic pronunciation features consisting ofa set of phone-pair distances were proposed for vowels and ap-plied to read speech. ... 8, no. 4, pp. 369–394, 1994. [24] N. Minematsu, S. Asakawa, and K.

20 Feb 2018: The Knowledge Engineering Review, Vol. 00:0, 1–24. c 2006, Cambridge University PressDOI: 10.1017/S000000000000000 Printed in the United Kingdom.

15 Jun 2018: Word levelconfidence scores are returned from the Kaldi [24] decoderwhich are frame weighted and undergo a piece-wise mappingfor use in error detection. ... 3660–3664. [24] D. Povey et al., “The Kaldi Speech Recognition Toolkit,” in Proc.of the

20 Feb 2018: 3.3. The agenda-based simulated user. The agenda-based user simulator [24, 25] factorises the user stateinto an agenda and a goal. ... 23] TopTable, “TopTable,” 2012, https://www.toptable.com. [24] J Schatzmann, Statistical User and Error Modelling

15 Jun 2018: 24,no. 8, pp. 1438–1449, 2016.

20 Feb 2018: In control tests by humanusers, the success rate of the system was 24.5% higher thanthe baseline Lets Go! ... Com-pared to the BASELINE system, the BUDSLETSGO systemimproves the dialogue success rate by 24.5% and the worderror rate by 9.7%.

20 Feb 2018: 24, no. 4, pp. 562–588, 2010. [13] M Gašić, C Breslin, M Henderson, D Kim, M Szummer,B Thomson, P Tsiakoulis, and S Young, “POMDP-based dia-logue manager adaptation

20 Feb 2018: SFRName Reward Success #Turnsbest prior 8.66 0.35 85.40 2.19 8.32 0.20adapted 9.62 0.30 89.60 1.90 8.24 0.19. ... The systemwas deployed in a telephone-based set-up, with subjects recruited via Ama-zon MTurk and a recurrent neural network model was used

20 Feb 2018: The static feature set comprised 24 Mel-Cepstral coefficients,logarithm of F0 and aperiodic energy components in five frequency. ... 12 sentences werethen randomly selected to make up a testset for each listener, leadingto 24 wave files pairs (12 for

20 Feb 2018: Computer Speech and Language,24(4):562–588. B Thomson, M Gašić, M Henderson, P Tsiakoulis, andS Young. ... Computer Speech and Language, 24(2):150–174. B Zhang, Q Cai, J Mao, E Chang, and B Guo.2001.

20 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.

20 Feb 2018: This mixed excitation model hasbeen shown to give significant improvements in the quality ofthe synthesized speech [24]. ... 63.5% 36.5%Male. CF-HMM. 75.5% 24.5%. 0% 25% 50% 75% 100%. Female.

20 Feb 2018: Hence, an itera-tive algorithm can be implemented which repeatedlyscans through the vocabulary, testing each word tosee if moving it to some other class would increasethe likelihood [24]. ... Thed p nuisance dimensions are modelled by a

20 Feb 2018: scr-10% 2.24 2.03 2.00 1.92. p <0.05, p <0.005Table 2: Human evaluation for utterance quality intwo domains.

20 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].

20 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]

12 Sep 2018: 23] L. Breiman. Bagging predictors. Machine learning,24(2):123–140, 1996. [24] O. Siohan, B. ... IEEE/ACM Transactions on Audio, Speech,and Language Processing, 24(8):1438–1449, 2016. Introduction. Graphemic English systems.

20 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.

3 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.

20 Feb 2018: 564 B. Thomson, S. Young / Computer Speech and Language 24 (2010) 562–588. ... B. Thomson, S. Young / Computer Speech and Language 24 (2010) 562–588 565.

20 Feb 2018: Yu. 2009. The Hidden InformationState model: a practical framework for POMDPbased spoken dialogue management.ComputerSpeech and Language, 24(2):150–174.

20 Feb 2018: 24, no. 4, Oct. 2010. [16] S. J. Young, G. Evermann, M.

20 Feb 2018: The feature set includes 24 spectralcoefficients, log F0 and 5 aperiodic component features.

20 Feb 2018: In Proceedings of ACL, 2017. [24] Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson, Milica Gašić, Pei-Hao Su, DavidVandyke, Tsung-Hsien Wen, and Steve Young. ... Computer Speech & Language, 24(2):150–174, 2010. [53] Steve Young, Milica

20 Feb 2018: g(i)jq =. T. t=1. v(t)ii d. (t)jq j, q = 1, , (d 1) (24). ... Markel,”Distance measures for speech processing”,IEEE Transactions on Acoustics, Speech, and Signal Processing, vol.ASSP-24, no.5, pp.380-391, October 1976.

13 Mar 2018: 2005. Ex-pressive speech-driven facial animation. ACM TOG 24, 4, 1283–1302. WANG, L., HAN, W., SOONG, F., AND HUO, Q.

13 Mar 2018: Comm. ACM, 24(6):381–395, 1981. [5] G.H. Golub and C.F. Van Loan, editors. ... Int. Journal of Computer Vision, 24(3):271–300,September 1997. [16] G. Xu and Z.

13 Mar 2018: 95. Table 2: Feature definitions. Features 1-24 Differences of mean and standarddeviation features based on Yuilleand Chen box features. ... Features 24-82 Differences of mean and standarddeviation features of 18 blocks, de-noted as ‘Extended

20 Feb 2018: 24, no. 4, pp. 562–588, 2010. [3] R. Sutton and A.

20 Feb 2018: The COMMUNICATOR systems in contrast onlyrequest between 24% and 43% of the unknown slots in each state.

15 Jun 2018: Theacoustic models are trained on 108.6 hours of BULATS test data(Gujarati L1 speakers) using the HTK v3.5 toolkit [24, 25].A Kneser-Ney trigram language model is trained ... INTERSPEECH, 2015. [24] S. Young et al., The HTK book (for HTK Version 3.4.1).

13 Mar 2018: 6] Cao, Y., Tien, W., Faloutsos, P. and Pighin, F., “Expressivespeech-driven facial animation”, ACM TOG, 24(4):1283–1302,2005.

13 Mar 2018: recognition from face motion manifolds.Image and Vision Computing, 24(5),. 2006. (in press). ... 24] R. O. Duda, P. E. Hart, and D. G. Stork.Pattern Classification.

13 Mar 2018: 2005. Ex-pressive speech-driven facial animation. ACM TOG 24, 4, 1283–1302. WANG, L., HAN, W., SOONG, F., AND HUO, Q.

20 Feb 2018: partition ex-plicitly records the fact that x = a and the existing partitionis updated to record the fact that x = ā [24].

13 Mar 2018: Puzicha. Shape matching and object recognition using shape contexts. PAMI,24(24):509–522, 2002. ... PAMI, 24(5),2002. [4] P. Dollár, Z. Tu, H. Tao, and S.

13 Mar 2018: scaling parameters, i. In particular:. 24. u1 u2 u3v1 v2 v31 1 1. ... u4v41. 35 =. 24. p11 p12 p13 p14p21 p22 p23 p24p31 p32 p33 p34.

20 Feb 2018: 24].3 Available at http://mi.eng.cam.ac.uk/˜farm2/emphasis.4 Cohen’s Kappa cannot be used here because the phrases are not distinct elements. ... Interspeech, 2010, pp. 410–413. [24] S. Young, G. Evermann, M. Gales, T.

20 Feb 2018: Thomson and Young2010] Blaise Thomson and SteveYoung. 2010. Bayesian update of dialogue state:A pomdp framework for spoken dialogue systems.Computer Speech and Language, 24:562–588.