Statistical Classification & Dialog Systems


Statistical Classification & Dialog Systems
Statistical Classification 


Technical support dialog systems: issues, problems, and solutions [PDF] from upenn.edu K Acomb, J Bloom, K Dayanidhi, P Hunter… – Proceedings of the …, 2007 – dl.acm.org … directed + natural language (SSLU) + limited mixed initia- tive Table 1: Evolution of spoken dialog systems. 26 … The overall accuracy of the system was considered rea- sonable for the state of the art of commercial SSLUs based on current statistical classification algorithms. … Cited by 38 – Related articles – All 21 versions

[PDF] Making grammar-based generation easier to deploy in dialogue systems [PDF] from pitt.edu D DeVault, D Traum… – Fifth INLG Conference, 2008 – cs.pitt.edu … very bad output or the necessity to author every utterance that comes with canned text or a competing statistical classification technique. … The method reduces the authoring bur- den associated with developing a grammar-based NLG component for an existing dialogue system. … Cited by 12 – Related articles – View as HTML – All 16 versions

Being bored? Recognising natural interest by extensive audiovisual integration for real-life application [PDF] from utwente.nl B Schuller, R Müller, F Eyben, J Gast… – Image and Vision …, 2009 – Elsevier Cited by 55 – Related articles – All 4 versions

Spoken Dialogue Systems K Jokinen… – Synthesis Lectures on Human …, 2009 – morganclaypool.com … Page 17. INTRoDUCTIoN To SPoKEN DIALoGUE SySTEMS 3 … This can be implemented using a statistical classification that determines the type of query along with named entity extraction to recognize the items in the query relevant to the class of query that has been identified. … Cited by 11 – Related articles – Library Search – All 5 versions

Emotion detection in dialog systems: applications, strategies and challenges [PDF] from syntheticspeech.de F Burkhardt, M van Ballegooy… – … , 2009. ACII 2009. …, 2009 – ieeexplore.ieee.org … with the same dialogs, such that the distribution of judgments could be measured and groups of users (eg low and high affinity to dialog systems) could be … Statistical classification is based on data and therefore data acquisition and labeling is vital for emotional analysis. … Cited by 3 – Related articles – All 2 versions

Intent Determination and Spoken Utterance Classification G Tur, L Deng – Spoken Language Understanding, 2011 – Wiley Online Library … The confidence value, c, optimizing the F-measure can also be used as the acceptance threshold in the actual spoken dialogue system. … Should the prompts/actions taken by the dialogue system change over time the semantic representation must also be changed. … Related articles – All 3 versions

Spoken language understanding using weakly supervised learning WL Wu, RZ Lu, JY Duan, H Liu, F Gao… – Computer Speech & …, 2010 – Elsevier … Traditionally, the SLU components in most spoken dialogue systems have been based on grammar-based parsers, which translate the input … It is a typical pattern classification problem and hence suitable to be dealt with by various kinds of statistical classification techniques. … Cited by 9 – Related articles – All 5 versions

From domain specification to virtual humans: An integrated approach to authoring tactical questioning characters [PDF] from usc.edu S Gandhe, D DeVault, A Roque… – … Annual Conference of …, 2008 – isca-speech.org … Index Terms: spoken dialogue systems, virtual humans 1. Introduction … The NLG uses the same statistical classification techniques, but mapping from dialogue acts to surface text. The NLG output can be modified by a style generator described below. 4.2. … Cited by 18 – Related articles – All 12 versions

Active Learning D Hakkani-Tür… – Spoken Language Understanding, 2011 – Wiley Online Library Page 1. 8 Active Learning Dilek Hakkani-Tür1 and Giuseppe Riccardi2 1 Microsoft Speech Labs, Microsoft Research, USA 2 University of Trento, Italy Statistical, data-driven approaches to spoken language processing have … Related articles – All 2 versions

Research on Recognition of Fillers in Spoken Dialogs F ZHAI… – Journal of Chinese Information Processing, 2011 – en.cnki.com.cn … influences the results of spoken language understanding and translation system.Based on the analysis and statistical classification of fillers … Academy of Sciences, Beijing 100080,China);The Disambiguation Strategy of Semantic Analysis in Spoken Dialogue Systems[J];Journal … Related articles – Cached

Emotion in Human-Computer Interaction C Peter… – Expanding the Frontiers of Visual Analytics and …, 2012 – Springer … The output must be split into separate features. 14.2.3.3 Classification Pattern recognition methods used to classify physiological data usually apply either statistical classification techniques or template matching schemes to the generated features. …

Attention, Sobriety Checkpoint! Can Humans Determine by Means of Voice, if Someone is Drunk… and Can Automatic Classifiers Compete? S Ultes, A Schmitt… – Twelfth Annual Conference of the …, 2011 – isca-speech.org … For Spoken Dialogue Systems (SDS) this knowledge can be used to render systems more adaptive and user friendly than they are nowadays. … 4. Statistical Classification For statistical classification, we used a total of 4368 acous- tic and prosodic features. … Related articles – All 2 versions

[PDF] Speaker Identification using Mel Frequency Cepstral Coefficient and BPNN [PDF] from ijarcsse.com K Dash, D Padhi, B Panda… – International Journal, 2012 – ijarcsse.com … Speaker verification integrated within a dialog system: If biometric authentication is desired in combination with a dialog system that performs automatic speech recognition … Few other techniques use the numerical values of the features coupled to statistical classification method. … View as HTML

[PDF] Hassan: A virtual human for tactical questioning [PDF] from ucla.edu D Traum, A Roque, A Leuski… – The 8th SIGdial …, 2007 – aroque.bol.ucla.edu … Another issue is that there are several different goals for dialogue systems, and optimizing on one may lead to sub- optimality for other goals. … 3.2 NPCEditor: Statistical Classification Our NPCEditor tool allows one to build statistical classifiers for “non-player characters”. … Cited by 24 – Related articles – View as HTML – All 16 versions

Natural language dialogue architectures for tactical questioning characters [PDF] from dtic.mil D Traum, A Leuski, A Roque, S Gandhe… – 2008 – DTIC Document … also had a goal of developing technology that educators who are expert at questioning but not necessarily experts at dialogue system technology could … is shown in Figure 2. The central component is the NPCEditor, a gen- eral tool used for statistical classification of language … Cited by 8 – Related articles – All 12 versions

The AT&T spoken language understanding system [PDF] from unitn.it N Gupta, G Tur, D Hakkani-Tur… – Audio, Speech, and …, 2006 – ieeexplore.ieee.org … State of the art statistical classification systems are trained using a large amount of labeled training data. Preparation of this data is labor intensive and time consuming. Furthermore, practical dialog systems are dynamic in nature. … Cited by 55 – Related articles – BL Direct – All 12 versions

[PDF] Quantification of Speech Rhythm in Norwegian as a Second Language [PDF] from lu.se WA van Dommelen – Lund Working Papers in Linguistics, 2009 – cts.lub.lu.se … For the five utterances investigated, statistical classification was to a large degree in congruence with LI group membership. … package for online real-time prosodic analysis that captures a number of prosodic features relevant for interaction control in spoken dialogue systems. … Cited by 1 – Related articles – View as HTML – All 11 versions

Far-field multimodal speech processing and conversational interaction in smart spaces [PDF] from epita.fr G Potamianos, J Huang, E Marcheret… – Hands-Free Speech …, 2008 – ieeexplore.ieee.org … processing – allowing for example better modeling of non-speech recognition, dialog systems, fusion, smart rooms. events. … performance in the far-field. A number of visual sensors are also We have developed a statistical classification approach for both … Cited by 6 – Related articles – All 5 versions

Query Log Analysis for Adaptive Dialogue-Driven Search [PDF] from psu.edu U Kruschwitz, N Webb… – Handbook of Web Log …, 2009 – books.google.com … Traditional artificial dialogue systems already allow users to interact with simple, structured data such as train or flight timetables (Zue, Glass, Goodine, Leung, Phillips, Polifroni & Seneff, 1990; Goddeau, Brill, Glass, Pao, Phillips, Polifroni, Seneff & Zue, 1994; Allen, Schubert … Cited by 4 – Related articles – All 7 versions

Generative and discriminative methods using morphological information for sentence segmentation of Turkish [PDF] from sri.com U Guz, B Favre, D Hakkani-Tur… – Audio, Speech, and …, 2009 – ieeexplore.ieee.org … handling bundles of features for each sample have been proposed [8]. FLMs have been successfully used for ASR of inflectional languages such as Arabic [9]. In this paper, we address the problem of exploiting morpho- logical information in statistical classification models for … Cited by 5 – Related articles – All 17 versions

Expression of affect in spontaneous speech: Acoustic correlates and automatic detection of irritation and resignation [PDF] from columbia.edu P Laukka, D Neiberg, M Forsell, I Karlsson… – Computer Speech & …, 2011 – Elsevier … Such corpora may consist of speech collected from, for example, spoken tutoring dialogues (Litman and Forbes-Riley, 2006), interactions with multi-modal dialogue systems (Vogt and André, 2005), television talk shows (Grimm et al., 2007), call-centers ( [20] and [Morrison et al … Cited by 14 – Related articles – All 6 versions

[PDF] Towards a standardization in the use of physiological signals for affective recognition systems [PDF] from shef.ac.uk J Arroyo-Palacios… – Measuring Behavior, 2008 – staffwww.dcs.shef.ac.uk … However, all the algorithms can be grouped on one of the three basic problems in statistical classification: (i) finding a map from features space to a set of labels; (ii) estimating the class given the training … 2004, Lecture Notes in Computer Science, Affective Dialogue Systems., pp … Cited by 13 – Related articles – View as HTML – All 7 versions

Architecture Model and Tools for Perceptual Dialog Systems J Curín… – Text, Speech and Dialogue, 2008 – Springer … For this use case of the meeting state recognition task, we used a SM with a statistical classification module trained off-line. … The dialog system of the CHIL Connector uses this knowledge to inform the calling party about the participant’s unavailability and blocks all incoming calls … Cited by 1 – Related articles – All 2 versions

Incorporating discourse features into confidence scoring of intention recognition results in spoken dialogue systems [PDF] from ntt.co.jp R Higashinaka, K Sudoh… – Speech communication, 2006 – Elsevier … There has been a tremendous amount of research in the field of speech understanding in spoken dialogue systems. … Similarly, statistical classification techniques have been used to detect relevant pieces of words in utterances ( [Kuhn and Mori, 1995] , [23] and [Béchet et al … Cited by 20 – Related articles – All 12 versions

An Aboriginal English ontology framework for Patient-Practitioner Interview Encounters D Forbes, A Sidhu… – Computer-Based Medical …, 2010 – ieeexplore.ieee.org … The Mayo Clinic is heading-up the effort to produce the 11th revision of the International Statistical Classification of Diseases and Related Health Problems (ICD), scheduled for release in 2015[2] . The previous … [9] T. Bickmore and T. Giorgino “Health dialog systems for patients … Cited by 1 – Related articles

Triangular-chain conditional random fields [PDF] from minwoojeong.com M Jeong… – Audio, Speech, and Language …, 2008 – ieeexplore.ieee.org … Statistical classification attempts can be mapped into two areas: sequential labeling and sequence classi- fication. … For example, the di- alog manager in the slot-filling spoken dialog system [10] re- quests information consisting of object names and user’s intent. … Cited by 13 – Related articles – All 6 versions

[BOOK] Incorporating Knowledge Sources Into Statistical Speech Recognition S Sakti, K Markov, S Nakamura… – 2009 – books.google.com … 141 5.2 Future Directions: A Roadmap to a Spoken Language Dialog System . . . . . … 136 5.1 Roadmap to spoken language dialog system incorporating other knowledge sources at higher ASR levels.. . . . … Cited by 2 – Related articles – Library Search – All 3 versions

Modeling Aspects of Multimodal Lithuanian Human-Machine Interface R Maskeliunas – Multimodal Signals: Cognitive and Algorithmic Issues, 2009 – Springer … of the semantic text will be a difficult problem for some time and designers of voice based dialog systems should impose … Previous experiments [15] showed the effectiveness of RDA approach comparing with other statistical classification methods (such as LDA, k-means, etc.) for … Cited by 3 – Related articles – All 3 versions

Dimensionality of dialogue act tagsets [PDF] from psu.edu A Popescu-Belis – Language Resources and Evaluation, 2008 – Springer … If all other things were equal, a smaller number of classes facilitates statistical classification, a fact illustrated for instance in an … technology, as focusing only on the literal functions of utterances might be acceptable for current human-computer dialogue systems, though it could … Cited by 8 – Related articles – BL Direct – All 12 versions

Introduction and Book Overview S Sakti, S Nakamura, K Markov… – … Knowledge Sources into …, 2009 – Springer … Therefore, the common core of the statistical classification perspective (Schuermann, 1996) is “learning by examples” from a collection of data. … Future directions are also discussed, focusing on how to incorporate the developed approaches in spoken language dialog systems.

A KNN-based Chinese generating method on static image description H Liu, X Wang… – Multimedia Technology (ICMT), …, 2011 – ieeexplore.ieee.org … has drawn more and more attention since 70s in last century and has been widely used in applications of summary, translation and dialogue system. … [11] D. Michie, Spiegelhalter, DJ, and Taylor, CC, eds, Machine learning, neural and statistical classification: Ellis Horwood … Related articles

Inductive and example-based learning for text classification [PDF] from microsoft.com YY Wang, X Li… – Ninth Annual Conference of the …, 2008 – isca-speech.org … Review data from the web can be used to train a sentiment classifier for spoken dialog systems like Voice-Rate [2], which allows callers to get or leave reviews for a product … Section 2 reviews the three different statistical classification algorithms that we investigated in this paper. … Cited by 1 – Related articles – All 6 versions

Emotion recognition for affective user interfaces using natural language dialogs [PDF] from postech.ac.kr C Lee… – … Communication, 2007. RO-MAN 2007. The …, 2007 – ieeexplore.ieee.org … various feature sets for textual input andpresent a hybrid method combining the keyword spotting features to statistical classification for recognizing … However, in task-oriented application like spoken dialog systems, it need the notion of application dependent emotions, and thus … Cited by 5 – Related articles – All 7 versions

Combining active and semi-supervised learning for spoken language understanding [PDF] from lip6.fr G Tur, D Hakkani-Tür… – Speech Communication, 2005 – Elsevier … State of the art statistical classification systems are trained using a large number of human-labeled utterances, preparation of which is labor … Spoken dialog systems aim to identify the intended meaning of human utterances, expressed in natural language, and to take actions … Cited by 84 – Related articles – All 12 versions

Transcription-Less Call Routing Using Unsupervised Language Model Adaptation [PDF] from comcast.net N Duta – Ninth Annual Conference of the International Speech …, 2008 – isca-speech.org … The NLU task is modeled as a statistical classification problem: the text corresponding to an utterance is assigned to one or more of a set of predefined user intents (routes). … J. Kuo, “Portability challenges in developing interactive dialogue systems”, in Proc. … Related articles – All 2 versions

Speech Driven Interaction in Mobile Multimodality GFF Corvino, FGP Petriccione… – … and pervasive services, 2009 – books.google.com … 296 Page 321. Speech Driven Interaction in Mobile Multimodality disambiguation, including probabilistic parsing and statistical classification. To … correlated? Point two of the list remands us to the analysis of basic dialog systems. User … Related articles

[PDF] Dialogue management for automatic troubleshooting and other problem-solving applications [PDF] from sigdial.org J Boye – Proc. of 8th SIGdial Workshop on Discourse and …, 2007 – sigdial.org … for achieving “VUI completeness” in the sense of Pieraccini and Huerta (2005), and thus a prerequi- site for a dialogue system to be … We will not consider this heterogeneous group of utterances in this article, as they are dealt with using statistical classification methods (see Boye … Cited by 10 – Related articles – View as HTML – All 5 versions

Hard vs. Fuzzy Clustering for Speech Utterance Categorization [PDF] from sinaidiagnostics.com A Albalate… – … in Multimodal Dialogue Systems, 2008 – Springer … A technical support automated agent is a spoken language dialog system devised to perform problem solving tasks over the phone in a similar … On the other end, it is com- pletely unclear if the category set and its definition are reasonable from the statistical classification point of … Related articles – BL Direct – All 8 versions

[PDF] A Compounds Generation Method Based on Visual Semantic Representation [PDF] from 220.194.54.16 H LIU, X WANG… – Chinese Journal of Electronics, 2011 – 220.194.54.16 … more and more attention since 70s in last century and has been widely used in applications such as automatic summary, machine translation and dialogue systems [1,2 … [16] Michie, D., Spiegelhalter, DJ et al., “Machine learning, neural and statistical classification”, Ellis Horwood … Related articles – View as HTML – All 4 versions

[PDF] Speech Technologies for Serbian and Kindred South Slavic Languages [PDF] from vnu.edu.vn V Delic, M Secujski, N Jakovljevic… – Advances in …, 2010 – tainguyenso.vnu.edu.vn … The paper is concluded by the directions of further research aimed at development of multimodal dialogue systems in South Slavic … Besides neural networks and maximum entropy models, the framework of statistical classification trees can also be effectively used for this purpose … Cited by 3 – Related articles – View as HTML – All 4 versions

Extending boosting for large scale spoken language understanding [PDF] from browsewith.us G Tur – Machine Learning, 2007 – Springer … Keywords Boosting · Semisupervised learning · Model adaptation · Cost-sensitive classification · Call classification · Spoken dialog systems 1 Introduction Statistical classification algorithms have long been studied in the machine learning commu- nity. … Cited by 3 – Related articles – BL Direct – All 16 versions

Measuring syntactic complexity in spontaneous spoken Swedish M Roll, J Frid… – Language and Speech, 2007 – las.sagepub.com … Two kinds of statistical classification algorithms (Bayesian and neural networks) were used to test this hypothesis. … We will then use statistical classification models to see how syntactic information can be used to predict whether att appears as fluent or disfluent. … Cited by 13 – Related articles – BL Direct – All 7 versions

[PDF] Building Ubiquitous and Robust Speech and Natural Language Interfaces I [PDF] from postech.ac.kr GG Lee… – … on Intelligent User Interfaces: Proceedings of …, 2007 – isoft.postech.ac.kr … Automatic Speech Recognition – (Spoken) Language Understanding • PART-II: Technology of Spoken Dialog Systems (80min) – Spoken Dialog Systems – Dialog Management – Dialog Studio … Page 30. 30 IUI 2007 tutorial Spoken Dialog System ASR SLU DM RG Models, … View as HTML – All 5 versions

MMSDS: ubiquitous computing and WWW-Based multi-modal sentential dialog system JH Kim… – Embedded and Ubiquitous Computing, 2006 – Springer … In this study, we suggest and implement Multi-Modal Sentential Dialog System (MMSDS) integrating 2 sensory channels with speech and … A statistical classification algorithms such as K-means clustering based on attributes into k partitions, QT (Quality Threshold) clustering that … Cited by 3 – Related articles – BL Direct – All 3 versions

An Improved Fusion Design of Audio-Gesture for Multi-modal HCI Based on Web and WPS JH Kim… – Embedded Software and Systems, 2007 – Springer … tracker, making it correct for a wide range of applications requiring high resolution, accuracy, and range [6], [7]. Statistical classification algorithms such as K … modes of interac- tion, http://www .w3.org/2002/mmi/ 2. M. Fuchs, P. et al.: Architecture of Multi-modal Dialogue System. … Related articles – BL Direct – All 3 versions

Approach to extended CSCW design based on embedded Korean sign language recognizer JH Kim… – Computer Supported Cooperative Work in Design III, 2007 – Springer … in various domains such as videoconference, messaging (instant messaging, e-mail) and collaborative software, including groupware and dialog systems. … Statistical classification algorithms such as K-means clustering, QT (Quality Thresh- old) clustering, the fuzzy c-means … Related articles – BL Direct – All 3 versions

A probabilistic approach to natural language disambiguation: semantic role labeling and dialogue act recognition [PDF] from polyu.edu.hk KC Lan – 2007 – repository.lib.polyu.edu.hk … 1.2 Disambiguation as Statistical Classification Many types of ambiguities are finite and definable, and thus can be tackled via classi- … tial improvements to our previous prototype-system called FNDS, which stands for Financial News Dialogue System (Lan et al., 2003, 2005). … Related articles – Library Search – All 2 versions

A Pattern Recognition-Based Multi-Modal HCI Using 3 Sensory Channels JH Kim, KB Lee… – Software Engineering Research, …, 2007 – ieeexplore.ieee.org … Statistical classification algorithms such as K-means clustering, QT (Quality Threshold) clustering, the fuzzy c-means clustering algorithm and the Self-Organizing Map (SOM), which have been ap-plied universally in traditional pattern recognition systems with unsupervised … Related articles – All 3 versions

A Post-Processing Approach to Improve Emotion Recognition Rates J Pittermann… – Signal Processing, 2006 8th …, 2006 – ieeexplore.ieee.org … During the past years the modeling of emotions, es- pecially in spoken language dialogue systems, has at- tracted interest within the … as described in [3]. A good comparison of classification methods is given in [4]. However, like other statistical classification methods, neural … Cited by 4 – Related articles – All 2 versions

Semi-supervised learning for spoken language understanding semantic role labeling [PDF] from cmu.edu G Tur, D Hakkani-Tur… – … Speech Recognition and …, 2005 – ieeexplore.ieee.org … Section 4 includes our experimental results using the AT&T VoiceTone R spoken dialog system data [4 … When a statistical classification model is trained with such labeled utterances, other sim- ilar utterances, such as account balance, may be labeled automatically with the same … Cited by 8 – Related articles – All 9 versions

[PDF] Robust Speaker Identification System [PDF] from iisc.ernet.in S Patra – 2007 – serc.iisc.ernet.in … 52 3.5 Statistical classification of transitional frames in an energy based voiced and unvoicedclassifier . . . . . … caller greetings, even personalized dialog systems can be built which can recognize the user, … Related articles – View as HTML

Spoken Language Understanding in Dialog Systems for Olympic Game Information J Liu, J Wang… – Industrial Informatics, 2006 IEEE …, 2006 – ieeexplore.ieee.org … It includes three main characteristics: 1) In a dialog system, the utterance is usually simple and expresses just one topic the user cares … It needs some knowledge about the domain, which can be obtained in two ways: from the data through a statistical classification, and from the …

Speech and Gesture Recognition-Based Robust Language Processing Interface in Noise Environment JH Kim… – Intelligent Data Engineering and Automated Learning …, 2006 – Springer … A statistical classification algorithms such as K-means clustering, QT (Quality Threshold) clustering, fuzzy c-means clustering algorithm and Self-Organizing Map (SOM) had been applied universally in a … 1. M. Fuchs, P. et al.: Architecture of Multi-modal Dialogue System. … Related articles – BL Direct – All 2 versions

[PDF] Dialogue Learning in CCBR [PDF] from ntnu.no HA Vartdal – 2007 – daim.idi.ntnu.no … 29 4.1.1.2 Question ranking . . . . . 30 4.1.2 Dialogue system . . . . . 30 4.1.2.1 Representing a dialogue . . . . . … 41 4.2.4 Dialogue system . . . . . 45 4.2.5 Putting the system together . . . . . … Related articles – View as HTML – All 4 versions

Discourse processing for explanatory essays in tutorial applications [PDF] from upenn.edu PW Jordan… – Proceedings of the 3rd SIGdial workshop on …, 2002 – dl.acm.org … the learning gains of 24 students to other sets of students in three other conditions; 1) a text control 2) human tutoring 3) another tutoring system that uses statistical classification only. … In Building Dialogue System for Tutorial Applications, Papers of the 2000 AAAI Fall Symposium … Cited by 17 – Related articles – All 55 versions

[PDF] Categorical prosody models for spoken language applications [PDF] from usc.edu S Ananthakrishnan – 2008 – digarc.usc.edu … Our solution is to incorporate canonical stress information from a public domain electronic pronunciation dictionary within the statistical classification framework. We show that this corpus-independent approach leads to significant gains in pitch accent … Related articles – View as HTML – All 7 versions

Discriminative training of natural language call routers [PDF] from ugm.ac.id HKJ Kuo… – Speech and Audio Processing, IEEE …, 2003 – ieeexplore.ieee.org Page 1. 24 IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, VOL. 11, NO. 1, JANUARY 2003 Discriminative Training of Natural Language Call Routers Hong-Kwang Jeff Kuo, Member, IEEE, and Chin-Hui Lee, Fellow, IEEE … Cited by 46 – Related articles – BL Direct – All 6 versions

Sentence verification in spoken dialogue system [PDF] from cmu.edu HM Wang… – Eighth European Conference on Speech …, 2003 – isca-speech.org … indispensable for spoken dialogue systems. … In this paper, the Support Vector Machine (SVM) is adopted as our classifier for its greater ability to generalize comparing to other statistical classification models [7]. The input of SVM is a scalar feature vector and the output is a scalar … Cited by 2 – Related articles – All 2 versions

Automatic labeling of semantic roles [PDF] from upenn.edu D Gildea… – Computational Linguistics, 2002 – MIT Press … of interpretation has additional uses outside of gen- eralizing information extraction, question answering, and semantic dialogue systems. … of syntactic parsing, part-of-speech tagging, and word sense disam- biguation, including probabilistic parsing and statistical classification. … Cited by 1063 – Related articles – BL Direct – All 90 versions

Lexicalized grammar 101 [PDF] from upenn.edu M Stone – Proceedings of the ACL-02 Workshop on Effective tools …, 2002 – dl.acm.org … abilistic and decision-theoretic modeling (including statistical classification, hidden Markov models and Markov decision processes) from the graduate-level AI foundations class. They might take NLP as a pre- liminary to research in dialogue systems or in learn- ing for language … Cited by 8 – Related articles – All 44 versions

A maximum entropy approach for spoken Chinese understanding [PDF] from ia.ac.cn G Xie, C Zong… – Computational Linguistics and Intelligent Text …, 2003 – Springer … Fig. 1. Spoken Language Translation System and Human-Machine Dialog System ASR TTS … Most natural language processing tasks can be reformulated as statistical classification problems, in which the task is to estimate the probability of class A occurring in context B [13]. … Related articles – BL Direct – All 11 versions

[PDF] Speaker recognition [PDF] from upatras.gr TD Ganchev – 2005 – wcl.ece.upatras.gr Page 1. Speaker Recognition Todor Dimitrov Ganchev Wire Communications Laboratory Department of Computer and Electrical Engineering University of Patras Greece Dissertation number: 169 November 2005 A dissertation … Cited by 19 – Related articles – View as HTML – All 4 versions

Natural Language Understanding DGD Jurafsky – Exploring Artificial Intelligence in the New …, 2003 – books.google.com … shallow semantic level of interpretation can be used for many purposes besides generalizing information extraction and semantic dialogue systems. … We then introduce the statistical classification technique used and examine in turn the knowledge sources our system makes … Related articles – All 2 versions

Prosodic and accentual information for automatic speech recognition [PDF] from psu.edu DH Milone… – Speech and Audio Processing, IEEE …, 2003 – ieeexplore.ieee.org … All these functions can be considered and incorpo- rated at either the phrase or word levels. They are of particular interest in dialogue systems where the pragmatic meaning of the phrases, in addition to their semantic content, needs to be captured [58]. … Cited by 19 – Related articles – BL Direct – All 10 versions

[PDF] Authors List [PDF] from atc.gr UJ Mylopoulos, UY Velegrakis, UA Pressa… – 2008 – openview.atc.gr Page 1. Cultural and historical digital libraries dynamically mined from news archives State of the Art Project Reference No. FP7-215874 Deliverable No. D2.1 Workpackage no: WP2: User and System Requirements Nature: R … Related articles – View as HTML – All 2 versions

Towards a road map on human language technology: Natural Language Processing A Eisele… – Proceedings of the 2002 COLING workshop …, 2002 – dl.acm.org … As similar capabilities are required for dialog systems in general, there will be significant synergy effects between these fields of research … So far, the methods used by the participants of SENSEVAL are mostly based on simple statistical classification using features extracted from … Cited by 2 – Related articles

[PDF] Confidence Measures for Speech/Speaker Recognition and Applications on Turkish LVCSR [PDF] from mengusoglu.eu E Mengusoglu – 2004 – mengusoglu.eu Page 1. Facult e Polytechnique de Mons Service de Th eorie deS CircuitS et de Traitement du Signal Confidence Measures for Speech/Speaker Recognition and Applications on Turkish LVCSR Erhan MENGUSOGLU Thèese … Related articles – View as HTML – All 9 versions

[PDF] WP10: A State of the Art Report on Human Computer Interfaces for Multimedia Retrieval [PDF] from tuc.gr M Perakakis, M Toutoudakis, AP TUC, S Toivonen… – 2004 – telecom.tuc.gr … 21 2 I terative dialog system design using ( optional) multi-stage data collection….. … I nChapter 5, we review efforts in defining design principles and creating tools forbuilding multimodal dialog systems with emphasis on the speech modality. … Related articles – View as HTML

[PDF] DIT-University of Trento Emotional Speech Synthesis: from theory to application. [PDF] from digns.com F Tesser – 2005 – static.digns.com Page 1. PhD Dissertation International Doctorate School in Information and Communication Technologies DIT – University of Trento Emotional Speech Synthesis: from theory to application. Fabio Tesser Advisor: Prof. Fabio Pianesi Universit`a degli Studi di Trento February 2005 … Related articles – View as HTML

[PDF] Towards a roadmap for Human Language Technologies: Dutch-Flemish experience [PDF] from uib.no D Binnenpoorte, C Cucchiarini… – Proceedings LREC …, 2002 – gandalf.aksis.uib.no … The following classes were defined: CALL (Computer Assisted Language Learning), access control, speech input, speech output, dialogue systems, document production, information access, and multilingual applications or translation modules. Page 23. … Cited by 7 – Related articles – View as HTML – All 17 versions

[PDF] A prosody based perspective for automated understanding of coverbal gestures [PDF] from psu.edu S Kettebekov – 2004 – etda.libraries.psu.edu … Chapter 1. Introduction 5 from an infrared camera that was used a dialog system for reference resolution [32]. iMAP, a vision-based framework for interaction with large screen displays has been evolving over the past four years at the Pennsylvania State University [33-36]. Its … Related articles – Library Search – All 6 versions