Random Forest & Dialog Systems


Random Forest & Dialog Systems
Random Forest (many decision trees)See also: 100 Best Decision Tree Videos | Decision Tree & Dialog Systems 2011


Emotion perception and recognition from speech CH Wu, JF Yeh, ZJ Chuang – Affective Information Processing, 2009 – Springer … NATURAL (Morrison et al., 2007) Sony acted corpus (Pierre-Yves, 2003) SVM (non-polynomial) 76.93(RBF kernel ) 91.5 (Gaussian kernel) KNN (K = 5) 75.85 85.2 Artificial neural networks 74.25 (Multilayer perception) 85.2 (Radial Basis Function) Random forest 71.98 — K … Cited by 11 Related articles All 4 versions 

[HTML] from sagepub.com Detection of Affective States From Text and Speech for Real-Time Human–Computer Interaction RA Calix, L Javadpour, GM Knapp – Human Factors: The Journal …, 2012 – hfs.sagepub.com … Results of the classification task using five emotion classes are presented in Table 8. Overall, the random forest and SVM classifiers performed … Finally, in dialogue systems, speakers do not have to describe the environment as in children’s stories, and they make substantial use … Cited by 1 Related articles All 4 versions 

[PDF] from emotion-research.net [PDF] The interspeech 2012 speaker trait challenge B Schuller, S Steidl, A Batliner, E Nöth… – Interspeech, …, 2012 – emotion-research.net … Main applications are found in intelligent and socially competent dialogue systems, agents and robots [1], as well as in the … Table 6: Personality, Likability, and Pathology Sub-Challenge baseline results by linear SVM and random forests (ensembles of unpruned REPTrees … Cited by 14 Related articles All 6 versions 

[PDF] from educationaldatamining.org [PDF] How to Classify Tutorial Dialogue? Comparing Feature Vectors vs. Sequences JP GONZÁLEZ-BRENES… – Proceedings of the …, 2011 – educationaldatamining.org … BREIMAN, L. 2004. Consistency for a simple model of random forests. 670, University of California, Berkeley, Berkeley. … ACL: HLT, 852-860. GONZÁLEZ-BRENES, JP, BLACK, AW and ESKENAZI, M. 2009. Describing Spoken Dialogue Systems Differences. … Cited by 1 Related articles All 7 versions 

[PDF] from uni-erlangen.de The hinterland of emotions: facing the open-microphone challenge S Steidl, A Batliner, B Schuller… – Affective Computing and …, 2009 – ieeexplore.ieee.org … however, not only means using spontaneous data, it means as well using all these data as in a dialog system, media retrieval or … Multinomial Naive Bayes (DMNB) [20], for the large feature space tasks together with Support-Vector Machines (SVM) and Random Forests for late … Cited by 22 Related articles All 13 versions 

[PDF] from aclweb.org [PDF] Feature weighting random forest for detection of hidden web search interfaces Y Ye, H Li, X Deng, JZ Huang – Computational Linguistics and Chinese …, 2009 – aclweb.org … [Received August 31, 2008; Revised February 23, 2009; Accepted February 16, 2009 ] Feature Weighting Random Forest for Detection of … In this approach, we have extended the random forest algorithm with a weighted feature selection method to build the individual classifiers. … Cited by 4 Related articles All 15 versions 

[PDF] from psu.edu Ensemble methods for spoken emotion recognition in call-centres D Morrison, R Wang, LC De Silva – Speech communication, 2007 – Elsevier … In (Petrushin, 2000) a system was built to monitor voice-mail messages in a call-centre and prioritise them with respect to emotional content. Similarly, in (Liscombe et al., 2005), prosodic and contextual features were used to identify emotion in a spoken dialog system. … Cited by 101 Related articles All 8 versions 

Computational emotion recognition using multimodal physiological signals: Elicited using Japanese kanji words K Takahashi, S Namikawa… – … and Signal Processing ( …, 2012 – ieeexplore.ieee.org … For computational emotion recognition, machine-learning approaches, such as multilayer neural networks, support vector machines, decision trees and random forests, are used to design emotion recognition systems and their characteristics are inves- tigated. … Related articles 

[PDF] from usc.edu Automatic detection of unnatural word-level segments in unit-selection speech synthesis WY Wang, K Georgila – Automatic Speech Recognition and …, 2011 – ieeexplore.ieee.org … We also compare three modeling methods based on Support Vector Machines (SVMs), Random Forests, and Conditional Random Fields (CRFs). … This can be very important in applications (eg adaptive spoken dialogue systems) where sentences are generated on the fly. … Related articles All 6 versions 

Editorial: Special Issue on Information Reuse and Integration R Alhajj, K Zhang – Special Issue: Information Reuse and Integration …, 2009 – informatica.si … The authors recommend using the random forest ensemble learning technique for building classification models from software measurement data … The paper by Shibata, Nishiguchi, and Tomiura discusses a type of open-ended dialog system that generates appropriated … All 2 versions 

Random forests-based confidence annotation using novel features from confusion network J Xue, Y Zhao – Acoustics, Speech and Signal Processing, 2006 …, 2006 – ieeexplore.ieee.org … Task-specific features have been also proposed, such as parsed-based features in dialog system [9] and semantic features in communicator … For confidence classification, we propose using Random Forests [11][12], which is a large set of decision trees that collectively decide … Cited by 20 Related articles All 2 versions 

[HTML] from hindawi.com Segmenting into adequate units for automatic recognition of emotion-related episodes: a speech-based approach A Batliner, S Steidl, D Seppi, B Schuller – Advances in Human-Computer …, 2010 – dl.acm.org Page 1. Hindawi Publishing Corporation Advances in Human-Computer Interaction Volume 2010, Article ID 782802, 15 pages doi:10.1155/2010/782802 Research Article Segmenting into Adequate Units for Automatic Recognition of … Cited by 28 Related articles All 22 versions 

[PDF] from dit.ie Benchmarking classification models for emotion recognition in natural speech: a multi-corporal study A Tarasov, SJ Delany – … and Workshops (FG 2011), 2011 IEEE …, 2011 – ieeexplore.ieee.org … Future work will consider extending the study to include some of the state-of-the-art classification algorithms includ- ing Random Forests [32], Gaussian Mixture Models [5] and Kernel … Influence of Contextual Information in Emotion Annotation for Spoken Dialogue Systems. … Cited by 2 Related articles All 2 versions 

Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method M Sheikhan, M Bejani, D Gharavian – Neural Computing & Applications, 2012 – Springer … [37] have proposed a decision tree-random forest ensemble hybrid feature selection algorithm that can be applied to a small-size dataset with a high number of features, and the potential benefits of continuous emotion models have been exploited in [55] through a 3-D model. … Cited by 1 Related articles 

[PDF] from thinkmind.org Classification on Speech Emotion Recognition-A Comparative Study T Iliou, CN Anagnostopoulos – … Journal on Advances in Life Sciences, 2010 – thinkmind.org … Multilayer Percepton, Random Forest, Probabilistic Neural Networks and Support Vector Machine were used for the Emotion Classification at seven classes namely … For example a dialog system might modulate its speech to be more puerile if it deems the emotional model of its … Related articles All 3 versions 

[PDF] from uni-erlangen.de Acoustic sleepiness detection: Framework and validation of a speech-adapted pattern recognition approach J Krajewski, A Batliner, M Golz – Behavior Research Methods, 2009 – Springer … Moreover, several different classifiers were used in our study, such as a decision tree (DT), a random forest, a naive Bayes, a basic rule learner, a radial basis function (RBF), a logistic base, a fuzzy lattice reasoning, and a logistic regression. … Cited by 20 Related articles All 13 versions 

[PDF] from kuleuven.be The automatic recognition of emotions in speech A Batliner, B Schuller, D Seppi, S Steidl… – Emotion-Oriented …, 2011 – Springer Page 1. The Automatic Recognition of Emotions in Speech Anton Batliner, Björn Schuller, Dino Seppi, Stefan Steidl, Laurence Devillers, Laurence Vidrascu, Thurid Vogt, Vered Aharonson, and Noam Amir Abstract In this chapter … Cited by 3 Related articles All 5 versions 

Modeling the Temporal Evolution of Acoustic Parameters for Speech Emotion Recognition S Ntalampiras, N Fakotakis – Affective Computing, IEEE …, 2012 – ieeexplore.ieee.org … of emo- tions in spoken language has become extremely impor- tant due to its immediate usage in many applications which include automatic dialog systems. … Fusion is conducted using various pattern recognition approaches, such as multilayer perceptron, random forest etc. … Cited by 1 Related articles All 11 versions 

[PDF] from dfki.de [PDF] Automatic classification of emotional states: purpose, possibilities, prospects A Batliner – prospects, 2008 – smartweb.dfki.de … Page 4. 4 ACES: types of databases • “information” dialogues – eg, automatic dialogue systems: user gets angry only sometimes, system should always be … (not yet: boosting, random forest, …) heretical suggestion: classifiers are not that important – at least at this stage … Related articles All 6 versions 

Soft computing in intelligent tutoring systems and educational assessment R Nielsen, W Ward, J Martin – Soft Computing Applications in Business, 2008 – Springer Page 1. B. Prasad (Ed.): Soft Computing Applications in Business, STUDFUZZ 230, pp. 201–230, 2008. springerlink.com © Springer-Verlag Berlin Heidelberg 2008 Soft Computing in Intelligent Tutoring Systems and Educational Assessment … Cited by 2 Related articles All 2 versions 

[PDF] from microsoft.com Calibration of confidence measures in speech recognition D Yu, J Li, L Deng – Audio, Speech, and Language Processing, …, 2011 – ieeexplore.ieee.org Page 1. Copyright (c) 2011 IEEE. Personal use is permitted. For any other purposes, Permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Cited by 1 Related articles All 5 versions 

[BOOK] Advances in Natural Language Processing: 6th International Conference, GoTAL 2008, Gothenburg, Sweden, August 25-27, 2008, Proceedings A Ranta, B Nordström – 2008 – books.google.com … Retrieval….. 222 Kimmo Kettunen De?nition Extraction with Balanced Random Forests….. 237 … Estimation….. 296 Tyne Liang and Dian-Song Wu A Grammar Formalism for Specifying ISU-Based Dialogue Systems…. 303 … All 4 versions 

A GPU Tile-Load-Map architecture for terrain rendering: theory and applications Y Amara, X Marsault – The Visual Computer, 2009 – Springer Page 1. Vis Comput (2009) 25: 805–824 DOI 10.1007/s00371-008-0305-1 ORIGINAL ARTICLE A GPU Tile-Load-Map architecture for terrain rendering: theory and applications Yacine Amara · Xavier Marsault Published online: 14 January 2009 © Springer-Verlag 2008 … Cited by 8 Related articles All 3 versions 

[PDF] from utep.edu Prosodic and temporal features for language modeling for dialog NG Ward, A Vega, T Baumann – Speech Communication, 2012 – Elsevier … It is worth noting that, since the time-until features involve future information, they would probably not be useful for dialog systems, although they would for offline applications such as transcription, voice search, and wordspotting. 4.2. Fillers, word fragments and laughter. … Cited by 5 Related articles All 7 versions 

Affective computation on EEG correlates of emotion from musical and vocal stimuli R Khosrowabadi, A Wahab, KK Ang… – … , 2009. IJCNN 2009. …, 2009 – ieeexplore.ieee.org … 265-280. [10] A. Haag, S. Goronzy, P. Schaich, and J. Williams, “Emotion Recognition Using Bio-sensors: First Steps towards an Automatic System,” in Affective Dialogue Systems. … 11, pp. 63-90, 1993. [38] L. Breiman, “Random Forests,” Machine Learning, vol. 45, pp. … Cited by 4 Related articles All 4 versions 

[PDF] from psu.edu [PDF] Using non-lexical context to improve a language model for dialog NG Ward, A Vega – Speech Communication, 2010 – Citeseer Page 1. Using Non-Lexical Context to Improve a Language Model for Dialog Nigel G. Ward, Alejandro Vega Computer Science, University of Texas at El Paso 500 West University Avenue, El Paso, Texas 79968 USA Abstract … Cited by 2 Related articles All 5 versions 

Predicting the Performance of a Financial Instrument GM O’rourke – US Patent 20,120,226,645, 2012 – freepatentsonline.com … SYSTEM AND METHOD FOR ROBUST EVALUATION OF THE USER EXPERIENCE IN AUTOMATED SPOKEN DIALOG SYSTEMS, April, 2010, … and regression tree (CART) model, a multivariate adaptive regression splines (MARS) model, and a random forests model, the … 

[PDF] from tu-muenchen.de [PDF] Ten Recent Trends in Computational Paralinguistics B Schuller, F Weninger – 4th COST, 2012 – mmk.e-technik.tu-muenchen.de … One main application is to increase efficiency and hence, user satisfaction in task oriented dialogue systems by enabling … continuous quantities including (extensions of) logistic regression, support vector regression, (recurrent) neural networks or random forests (ensembles of … Related articles All 2 versions 

A spoken dialogue system based on keyword spotting technology P Zhang, Q Zhao, Y Yan – Human-Computer Interaction. HCI Intelligent …, 2007 – Springer … Higashinaka, R., Sudoh, K., Nakano, M.: Incorporating Discourse Features into Confi- dence Scoring of Intention Recognition Results in Spoken Dialogue Systems. … Xue, J., Zhao, Y.: Random Forests-based Confidence Annotation Using Novel Features from Confusion Network. … Related articles BL Direct All 3 versions 

[PDF] from proceedings.com [PDF] SLT 2008 HINN GOA – 2008 – toc.proceedings.com … Paper 12: “WHO IS THIS” QUIZ DIALOGUE SYSTEM AND USERS’ ….149 EVALUATION Minako … Paper 1: MORPHOLOGICAL RANDOM FORESTS FOR LANGUAGE …..189 MODELING OF INFLECTIONAL LANGUAGES Ilya … All 3 versions 

Emotion recognition improvement using normalized formant supplementary features by hybrid of DTW-MLP-GMM model D Gharavian, M Sheikhan, F Ashoftedel – Neural Computing & …, 2012 – Springer … selection (SFFS) [19, 20], forward feature selection (FFS), and backward feature selection (BFS) [11], principal component analysis (PCA) or linear discriminant analysis (LDA) [21], fast correlation- based filter (FCBF) [22], and decision tree-random forest ensemble hybrid … Cited by 1 Related articles 

[PDF] from cnrs.fr Whodunnit–searching for the most important feature types signalling emotion-related user states in speech A Batliner, S Steidl, B Schuller, D Seppi, T Vogt… – Computer Speech & …, 2011 – Elsevier In this article, we describe and interpret a set of acoustic and linguistic features that characterise emotional/emotion-related user states – confined to the. Cited by 46 Related articles All 11 versions 

Private emotions versus social interaction: a data-driven approach towards analysing emotion in speech A Batliner, S Steidl, C Hacker, E Nöth – User Modeling and User-Adapted …, 2008 – Springer Page 1. User Model User-Adap Inter (2008) 18:175–206 DOI 10.1007/s11257-007-9039-4 ORIGINAL PAPER Private emotions versus social interaction: a data-driven approach towards analysing emotion in speech Anton Batliner · Stefan Steidl · Christian Hacker · Elmar Nöth … Cited by 53 Related articles BL Direct All 3 versions 

Physiological signals based human emotion Recognition: a review S Jerritta, M Murugappan… – Signal Processing and …, 2011 – ieeexplore.ieee.org … K Nearest Neighbor 62.70 (User Independent) Random Forest 62.41(User Independent) … P. Heisterkamp, A. Haag, S. Goronzy, P. Schaich, and J. Williams, “Emotion Recognition Using Bio- sensors: First Steps towards an Automatic System,” in Affective Dialogue Systems. vol. … Cited by 3 Related articles 

[PDF] from gla.ac.uk [PDF] Towards a Technology of Nonverbal Communication: Vocal Behavior in Social and Affective Phenomena A Vinciarelli, G Mohammadi – Affective Computing and Interaction: …, 2011 – dcs.gla.ac.uk Page 1. Towards a Technology of Nonverbal Communication: Vocal Behavior in Social and Affective Phenomena Alessandro Vinciarelli University of Glasgow – Department of Computing Science Sir Alwyn Williams Building … Cited by 2 Related articles All 7 versions 

[PDF] from ox.ac.uk Claros-bringing classical art to a global public D Kurtz, G Parker, D Shotton, G Klyne… – e-Science, 2009. e- …, 2009 – ieeexplore.ieee.org … We use a random forest of KD trees for this [3]. In summary, by first processing all the vases to obtain their shape descriptors, and then … [4] D. Field, R. Catizone, W. Cheng, A. Dingli, S. Worgan, L. Ye, and Y. Wilks, “The Senior Companion: a Semantic Web Dialogue System, Proc. … Cited by 9 Related articles All 20 versions 

Automated communication analysis of teams PW Foltz, MJ Martin – Team Effectiveness in Complex …, 2008 – books.google.com … learning techniques have been applied to discourse modeling, generally for the purpose of improving speech recognition and dialogue systems. … Hill-climbing methods (eg, step- wise regression, random forests, support vector machines) are then used to select a subset of the … Cited by 10 Related articles 

Automatic stress detection in emergency (telephone) calls I Lefter, LJM Rothkrantz, DA Van Leeuwen… – International Journal of …, 2011 – Inderscience … was used with the help of Wizard of Oz (WoZ) scenarios (Steidl et al., 2008) or computer-based dialogue systems (Zeng et al … 1999; Krajewski and Kroger, 2007), hidden Markov models (HMM) (Vlasenko et al., 2007), BNs (Schuller et al., 2005a), random forests, support vector … Cited by 6 Related articles All 4 versions 

[HTML] from rug.nl [HTML] ACL Logo ACL Anthology CM Translation, ISMTU Paraphrases – Computational Linguistics, 2007 – acl.eldoc.ub.rug.nl … W12-0511 [bib]: Michael Bloodgood; Peng Ye; Paul Rodrigues; David Zajic; David Doermann A Random Forest System Combination … Nina Dethlefs; Helen Hastie; Verena Rieser; Oliver Lemon Optimising Incremental Generation for Spoken Dialogue Systems: Reducing the … All 6 versions 

[PDF] from idiap.ch [PDF] TROPE GMA Vinciarelli – 2012 – publications.idiap.ch Page 1. TROPE R HCRAESE R PAID I TOWARDS A TECHNOLOGY OF NONVERBAL COMMUNICATION: VOCAL BEHAVIOR IN SOCIAL AND AFFECTIVE PHENOMENA Gelareh Mohammadi Alessandro Vinciarelli Idiap-RR-05-2012 JANUARY 2012 … Related articles 

[PDF] from rodneynielsen.com [BOOK] Learner answer assessment in intelligent tutoring systems RD Nielsen – 2007 – books.google.com Page 1. LEARNER ANSWER ASSESSMENT IN INTELLIGENT TUTORING SYSTEMS by RODNEY D. NIELSEN MS, University of Colorado, Boulder, 2005 A thesis submitted to the Faculty of the Graduate School of the University … Cited by 1 Related articles All 7 versions 

[PDF] from kuleuven.be Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge B Schuller, A Batliner, S Steidl, D Seppi – Speech Communication, 2011 – Elsevier More than a decade has passed since research on automatic recognition of emotion from speech has become a new field of research in line with its ‘big brothers. Cited by 54 Related articles All 10 versions 

[PDF] from cmu.edu [PDF] Improving the Performance of LVCSR Using Ensemble of Acoustic Models R Zhang – 2006 – cs.cmu.edu … solving complicated classification problems. Some general methods for constructing ensembles have been developed, such as Boosting, Bagging, Random Space, Random Forests, etc.. Meantime, speech-specific methods … Related articles 

[PDF] from psu.edu [PDF] Making an Effective Use of Speech Data for Acoustic Modeling R Zhang – 2007 – Citeseer Page 1. Making an Effective Use of Speech Data for Acoustic Modeling Rong Zhang CMU-LTI-07-016 Language Technologies Institute School of Computer Science Carnegie Mellon University 5000 Forbes Ave., Pittsburgh, PA 15213 www.lti.cs.cmu.edu Thesis Committee: … Cited by 3 Related articles All 4 versions 

[PDF] from sydney.edu.au Detecting Naturalistic Expressions of Nonbasic Affect using Physiological Signals O AlZoubi, S D’Mello, R Calvo – 2012 – ieeexplore.ieee.org … using only physiological features [33] yes (16) EMG, ECG, RESP, GSR 9 IAPS Self report Simba / Knn(1), Random Forests (WT) 10 CV %48, %68 and %69 for happiness, disgust and fear [6] yes ECG, EMG, GSR, RESP 3 music objective (deter- mined by stimu- lus type) … Related articles All 7 versions 

[PDF] from limsi.fr [PDF] Language Models for Automatic Speech Recognition of Inflectional Languages I Oparin – 2008 – limsi.fr … It was Lukáš Burget who once told me: “Ilya, I think this random forest stuff is really worth trying … in some form for any language technology application: optical character recognition, document classification, machine translation, speech synthesis, dialog systems, natural language … Cited by 3 Related articles All 3 versions 

[PDF] from umsystem.edu Improvement of Decoding Engine & Phonetic Decision Tree in Acoustic Modeling for Online Large Vocabulary Conversational Speech Recognition J Xue – 2007 – mospace.umsystem.edu … 18 3.1 Fast Confusion Network Algorithm……………18 3.2 Extended Confusion Network Algorithm……………21 Chapter 4……………23 Random Forests-based Confidence Annotation … Related articles All 3 versions 

Cross-corpus acoustic emotion recognition: Variances and strategies B Schuller, B Vlasenko, F Eyben… – Affective Computing, …, 2010 – ieeexplore.ieee.org … With respect to static classification, the list of classifiers seems endless: neural networks (mostly Multi- Layer Perceptrons) [75], Bayes classifier [67], Baysian Networks [88], [90], Gaussian Mixture Models [71], [91], Decision Trees [92], Random Forests [93], k-Nearest Neighbor … Cited by 22 Related articles All 8 versions 

[PDF] from umd.edu Machine learning for the New York City power grid C Rudin, D Waltz, RN Anderson… – Pattern Analysis and …, 2012 – ieeexplore.ieee.org Page 1. Machine Learning for the New York City Power Grid Cynthia Rudin, David Waltz, Senior Member, IEEE, Roger N. Anderson, Member, IEEE, Albert Boulanger, Member, IEEE, Ansaf Salleb-Aouissi, Maggie Chow, Haimonti … Cited by 12 Related articles All 15 versions 

[PDF] from aclweb.org Modeling Regular Polysemy: A Study on the Semantic Classification of Catalan Adjectives G Boleda, S Schulte im Walde, T Badia – Computational Linguistics, 2012 – MIT Press … this article. The semantic properties of adjectives can also be exploited in advanced NLP tasks and applications such as Question Answering, Dialog Systems, Natural Language Generation, or Information Extraction. For instance … Cited by 1 Related articles All 8 versions 

[PDF] from mit.edu [PDF] Machine Learning for the New York City Power Grid PN Gross, B Huang, S Ierome, DF Isaac… – … ON PATTERN ANALYSIS …, 2012 – mit.edu Page 1. Machine Learning for the New York City Power Grid Cynthia Rudin, David Waltz, Senior Member, IEEE, Roger N. Anderson, Member, IEEE, Albert Boulanger, Member, IEEE, Ansaf Salleb-Aouissi, Maggie Chow, Haimonti … Related articles 

[PDF] from arxiv.org Learning Symbolic Models of Stochastic Domains LP Kaelbling, HM Pasula, LS Zettlemoyer – arXiv preprint arXiv:1110.2211, 2011 – arxiv.org Page 1. Journal of Artificial Intelligence Research 29 (2007) 309-352 Submitted 6/06; published 7/07 Learning Symbolic Models of Stochastic Domains Hanna M. Pasula pasula@csail.mit.edu Luke S. Zettlemoyer lsz@csail.mit.edu Leslie Pack Kaelbling lpk@csail.mit.edu … Related articles All 3 versions 

[PDF] from utwente.nl [BOOK] How does real affect affect affect recognition in speech? KP Truong – 2009 – doc.utwente.nl … as being in stress. Interaction with machines, robots or spoken dialog systems in call centers, will feel much more natural and will be much more effective if human emotions can be recognized. Some research communities aim … Cited by 2 Related articles All 9 versions 

[PDF] from uwaterloo.ca cROVER: Context-augmented Speech Recognizer based on Multi-Decoders’ Output MK Abida – 2011 – uwspace.uwaterloo.ca Page 1. cROVER: Context-augmented Speech Recognizer based on Multi-Decoders’ Output by Mohamed Kacem Abida A thesis presented to the University of Waterloo in fulfillment of the thesis requirement for the degree of Doctor of Philosophy in … Related articles All 5 versions 

[PDF] from xesoftware.com.au [PDF] Early Stage Detection of Speech Recognition Errors S Choularton – 2007 – xesoftware.com.au … 5.20 Using Random Forest to predict errors when trained on Set 1. . . . . 129 5.21 Using Random Forest to predict errors when trained on Set 2. . . . . 130 … of this thesis. 1.2.1 Automatic Speech Recognition Spoken dialogue systems are prone to failure during use. … Related articles 

Web resources for language modeling in conversational speech recognition I Bulyko, M Ostendorf, M Siu, T Ng, A Stolcke… – ACM Transactions on …, 2007 – dl.acm.org Page 1. 1 Web Resources for Language Modeling in Conversational Speech Recognition IVAN BULYKO BBN Technologies MARI OSTENDORF University of Washington MANHUNG SIU and TIM NG Hong Kong University … Cited by 38 Related articles All 2 versions 

[PDF] from washington.edu Learning symbolic models of stochastic domains HM Pasula, LS Zettlemoyer, LP Kaelbling – Journal of Artificial Intelligence …, 2007 – aaai.org Page 1. Journal of Artificial Intelligence Research 29 (2007) 309-352 Submitted 6/06; published 7/07 Learning Symbolic Models of Stochastic Domains Hanna M. Pasula pasula@csail.mit.edu Luke S. Zettlemoyer lsz@csail.mit.edu Leslie Pack Kaelbling lpk@csail.mit.edu … Cited by 80 Related articles All 19 versions 

[PDF] from archives-ouvertes.fr Construction et stratégie d’exploitation des réseaux de confusion en lien avec le contexte applicatif de la compréhension de la parole B Minescu – 2008 – tel.archives-ouvertes.fr … We use France Telecom spoken dialogue system for customer care. Two issues inherent to this context are tackled. A dialogue system does not only have to recognize what a user says but also to unders- tand the meaning of his request and to act upon it. … Related articles All 5 versions