Conditional Random Fields & Dialog Systems 2013


See also:

Conditional Random Fields & Dialog Systems 2014Conditional Random Fields & Dialog Systems 2015


POMDP-based statistical spoken dialog systems: A review S Young, M Gasic, B Thomson… – Proceedings of the …, 2013 – ieeexplore.ieee.org … Spoken Dialog Systems: A Review … I. INTRODUCTION Spoken dialog systems (SDSs) allow users to interact with a wide variety of information systems using speech as the primary, and often the only, communication medium [1]–[3]. Traditionally, SDSs have been mostly … Cited by 16 Related articles All 6 versions Cite Save

Dimensional affect recognition using continuous conditional random fields T Baltrusaitis, N Banda… – Automatic Face and …, 2013 – ieeexplore.ieee.org … We propose the use of Continuous Conditional Random Fields (CCRF) in combination with Support Vector Machines for Regression (SVR) for modeling continuous emotion in dimensional space. … [20] proposed the use of Latent Dynamic Conditional Random Fields (LDCRF). … Cited by 4 Related articles All 5 versions Cite Save

Toward information theoretic human-robot dialog S Tellexll, P Thakerll, R Deitsl, D Simeonovl, T Kollar… – Robotics, 2013 – books.google.com … Furthermore, it chooses targeted questions based on the robot’s model of the external world. Existing work in dialog systems [3, 12, 20, 22] use MDP and POMDP models with a ?xed, prede?ned state space to represent the user’s intentions. … Cited by 12 Related articles All 9 versions Cite Save

Asgard: A portable architecture for multilingual dialogue systems J Liu, P Pasupat, S Cyphers… – Acoustics, Speech and …, 2013 – ieeexplore.ieee.org … the portability issue from the language understanding perspective and present the Asgard architecture, a CRF-based (Conditional Random Fields) and crowd-sourcing-centered framework, which supports expert-free development of multilingual dialogue systems and seamless … Cited by 2 Related articles All 4 versions Cite Save

Learning environmental knowledge from task-based human-robot dialog T Kollar, V Perera, D Nardi… – Robotics and Automation ( …, 2013 – ieeexplore.ieee.org … language commands for service tasks, 2) a knowledge base that represents the mapping from referring expressions to locations and actions 3) a dialog system that is able … The model is learned as a conditional random field (CRF); we use gradient descent (LBFGS) to optimize … Cited by 4 Related articles All 3 versions Cite Save

FudanNLP: A toolkit for Chinese natural language processing X Qiu, Q Zhang, X Huang – Proceedings of ACL, 2013 – Citeseer … Currently, our toolkit has been used by many universities and companies for various applications, such as the dialogue system, so- cial computing, recommendation system and vertical search. … Chi- nese segmentation and new word detection us- ing conditional random fields. … Cited by 6 Related articles All 6 versions Cite Save More

Semantic Parsing Using Word Confusion Networks With Conditional Random Fields G Tur, A Deoras, D Hakkani-Tur – Proc. of the INTERSPEECH, 2013 – msr-waypoint.com … The state of the art approaches for semantic parsing rely on using discriminative sequence classification methods, such as conditional random fields (CRFs). Most dialog systems em- ploy a cascaded approach where the best hypotheses from the ASR system are fed into the … Cited by 1 Related articles All 6 versions Cite Save

Conditional Random Fields for Responsive Surface Realisation Using Global Features N Dethlefs, H Hastie, H Cuayáhuitl… – Proceedings of ACL, …, 2013 – macs.hw.ac.uk … In interactive settings such as gen- eration within a spoken dialogue system (SDS), a … We use conditional random fields (Lafferty et al., 2001; Sutton and McCallum, 2006), which are suitable for modelling rich contexts, in combination with semantic trees for rich linguistic … Cited by 2 Related articles All 10 versions Cite Save More

Recipe For Building Robust Spoken Dialog State Trackers: Dialog State Tracking Challenge System Description S Lee, M Eskenazi – Submitted to SIGDIAL, 2013 – newdesign.aclweb.org … A. Raux and Y. Ma, 2011. Efficient Probabilistic Tracking of User Goal and Dialog History for Spoken Dialog Systems. In Proceedings of Interspeech. C. Sutton and A. McCallum, 2006. An Introduction to Conditional Random Fields for Relational Learning. … Cited by 2 Related articles All 8 versions Cite Save More

Latent mixture of discriminative experts D Ozkan, LP Morency – Multimedia, IEEE Transactions on, 2013 – ieeexplore.ieee.org … Our experiments are performed on a dataset of 45 storytelling dyadic interactions [4]1. We compare our LMDE model with previous approaches based on Conditional Random Fields (CRF) [5], Latent- Dynamic CRFs [6], and CRF Mixture of Experts (aka Logarithmic Opinion … Cited by 4 Related articles All 5 versions Cite Save

An empirical investigation of sparse log-linear models for improved dialogue act classification YN Chen, WY Wang, AI Rudnicky – Acoustics, Speech and …, 2013 – ieeexplore.ieee.org … For instance, conditional random fields (CRF) [22, 23], support vector machine (SVM) [12, 24, 25], maximum entropy (lo- gistic regression) [10, 13, 16 … 1] Jason D. Williams and Steve Young, “Partially observable Markov decision processes for spoken dialog systems,” Com- puter … Cited by 2 Related articles All 3 versions Cite Save

Interpreting situated dialogue utterances: an update model that uses speech, gaze, and gesture information C Kennington, S Kousidis… – Proceedings of SIGdial …, 2013 – pub.uni-bielefeld.de … The model is trained on conversational data and can be used as an understanding module in an incremen- tal, situated dialogue system. … our model types work better than (Heintze et al., 2010) which used support vec- tor machines and conditional random fields, and (Peldszus … Cited by 4 Related articles All 8 versions Cite Save More

Structured Discriminative Model For Dialog State Tracking S Lee – Submitted to SIGDIAL, 2013 – newdesign.aclweb.org … A. Raux and Y. Ma, 2011. Efficient Probabilistic Tracking of User Goal and Dialog History for Spoken Dialog Systems. In Proceedings of Interspeech. C. Sutton and A. McCallum, 2006. An Introduction to Conditional Random Fields for Relational Learning. … Cited by 1 Related articles All 7 versions Cite Save More

Clarifying commands with information-theoretic human-robot dialog R Deits, S Tellex, P Thaker… – Journal of Human …, 2013 – humanrobotinteraction.org … At inference time, these locally normalized factors can be simply multiplied together without the need to compute a global normalization constant, as would be required for a Markov random field or conditional random field. 61 Page 5. … Cited by 5 Related articles All 7 versions Cite Save

Exploiting deep neural networks for detection-based speech recognition SM Siniscalchi, D Yu, L Deng, CH Lee – Neurocomputing, 2013 – Elsevier … space. Neural networks have also been used to model state and transition features in conditional random field (CRF) based ASR systems (eg, [17]), in beam search pruning [18] and confidence measure estimation [19] and [20]. … Cited by 14 Related articles All 9 versions Cite Save

Comparison and Combination of Lightly Supervised Approaches for Language Portability of a Spoken Language Understanding System B Jabaian, L Besacier, F Lefevre – Audio, Speech, and …, 2013 – ieeexplore.ieee.org … module of a dialogue system. We show that the use of statistical machine translation (SMT) can reduce the time and the cost of porting a system from a source to a target language. For conceptual decoding, a state-of-the-art module based on conditional random fields (CRF) is … Cited by 2 Related articles All 3 versions Cite Save

Modeling user behavior online for disambiguating user input in a spoken dialogue system F Wang, K Swegles – Speech Communication, 2013 – Elsevier … conditional random field method, a two-phase data-driven domain-specific user utterance simulation method, and a linguistic knowledge-based ASR channel simulation method. They proposed a data-driven user simulation for automated evaluation of spoken dialogue systems. … Cited by 2 Related articles All 4 versions Cite Save

Joint Discriminative Decoding of Word and Semantic Tags for Spoken Language Understanding A Deoras, G Tur, R Sarikaya, D Hakkani-Tur – 2013 – ieeexplore.ieee.org … when compared to a very strong cascade baseline comprising of state-of-the-art large vocabulary ASR followed by conditional random field (CRF) based slot sequence tagger. … models, such as conditional random fields, (CRFs) [10], for modeling. More formally, slot filling is … Cited by 2 Related articles All 8 versions Cite Save

Leveraging knowledge graphs for web-scale unsupervised semantic parsing L Heck, D Hakkani-Tür, G Tur – 2013 – research.microsoft.com … labels from the set of slots/concepts C. Following the state-of-the-art approaches for entity extraction (eg, [2, 3]), we use discrimi- native conditional random fields (CRFs)[18 … [10] M. Araki and D. Takegoshi, “Framework for the devel- opment of spoken dialogue system based in … Cited by 2 Related articles All 6 versions Cite Save

On the Many Interacting Flavors of Planning for Robotics K Talamadupula, M Scheutz, G Briggs, S Kambhampati – 2013 – tahoma.eas.asu.edu … gainfully. On the one hand, dialogue systems provide more information and context to task planners in the form of instructions (goals), actions models and user prefer- ences. … 2007. Conditional random fields for ac- tivity recognition. … Cited by 1 Related articles All 6 versions Cite Save More

A noisy channel approach to error correction in spoken referring expressions SN Kim, I Zukerman, T Kleinbauer… – Proceedings of the 6th …, 2013 – aclweb.org … Additional – words that are often superfluous, eg, “the mug that is on the table”. We employed the Mallet implementation of the linear chain Conditional Random Fields (CRF) al- gorithm (Lafferty et al., 2001) to learn sequences of semantic labels (mallet.cs.umass.edu). … Cited by 1 Related articles All 5 versions Cite Save More

LSTM-modeling of continuous emotions in an audiovisual affect recognition framework M Wöllmer, M Kaiser, F Eyben, B Schuller… – Image and Vision …, 2013 – Elsevier … emotion recognition can be found in the areas of human–robot communication, call center dialog systems, computer games … showing that LSTM architectures outperform Support Vector Machines (SVM), Support Vector Regression (SVR), and Conditional Random Fields (CRF). … Cited by 13 Related articles All 8 versions Cite Save

Dialog State Tracking using Conditional Random Fields H Ren, W Xu, Y Zhang, Y Yan – newdesign.aclweb.org … In Proceedings of the 2006 AAAI Workshop on Statistical and Empiri- cal Approaches for Spoken Dialogue Systems, pages 13–18, Menlo Park, California. The AAAI Press. John Lafferty, Andrew Mccallum, and Fernando Pereira. 2001. Conditional random fields: Prob- abilistic … Related articles All 7 versions Cite Save More

Open-domain Utterance Generation for Conversational Dialogue Systems using Web-scale Dependency Structures H Sugiyama, T Meguro, R Higashinaka, Y Minami – sigdial.org … The template-based approach resembles previous rule- based approaches, but these dialogue systems had difficulty achieving coverage for template … dependency parser we use is a state-of-the-art Japanese dependency parser that uses Conditional Random Fields trained on … Cited by 1 All 7 versions Cite Save More

An investigation of single-pass ASR system combination for spoken language understanding F Bougares, M Rouvier, N Camelin, P Deléglise… – Statistical Language and …, 2013 – Springer … we present a study which evaluates the benefits provided by a single-pass ASR exchange-based combination approach for spoken dialog system. … in a slot sequence tagging for spoken language, and such SLU module are usually based on Conditional Random Fields (CRF) [4 … Related articles All 4 versions Cite Save

Active Learning for Speech Emotion Recognition Using Conditional Random Fields Z Zhao, X Ma – … Distributed Computing (SNPD), 2013 14th ACIS …, 2013 – ieeexplore.ieee.org … To address these issues, we propose a modified information density query strategy based on Conditional Random Fields, which is formulated as … Kroul, J. Nouza, and J. Silovsk y, “Two-Level Fusion to Improve Emotion Classification in Spoken Dialogue System,” Lecture Notes … Related articles All 2 versions Cite Save

Extracting hierarchical data points and tables from scanned contracts J Stadermann, S Symons, I Thon – … Management Architecture (UIMA), 2013 – ceur-ws.org … For table extraction, heuristic methods [8] have been proposed as well as Conditional Random Fields [7]. In contrast, our system uses a theoretically … Our work follows strategies commonly used in spoken dialogue systems [4] and uses a set of small classifiers which is inspired … Related articles All 2 versions Cite Save More

Constructing Language Models for Spoken Dialogue Systems from Keyword Set K Komatani, S Mori, S Sato – … Challenges and Solutions in Applied Artificial …, 2013 – Springer … EACL, pp. 157–165 (2009) 7. Hakkani-Tur, D., Rahim, M.: Bootstrapping language models for spoken dialog systems from the world wide web. In: Proc. … Kudo, T., Yamamoto, K., Matsumoto, Y.: Applying conditional random fields to Japanese morphological analysis. In: Proc. … Related articles All 2 versions Cite Save

Counseling Dialog System with 5W1H Extraction S Han, K Lee, D Lee, GG Lee – sigdial.org … We used the conditional random field algo- rithm to extract 5W1H information, and con- structed our counseling algorithm using a dia- log … Developing a counseling dialog system could be an effective solution to address this problem because the system has no limitations with … Related articles All 7 versions Cite Save More

Demonstration of the Parlance system: a data-driven, incremental, spoken dialogue system for interactive search H Hastie, MA Aufaure, P Alexopoulos, H Cuayáhuitl… – aclweb.org … Optimising Incremental Generation for Spoken Dialogue Systems: Reducing the Need for Fillers. In Proceedings of INLG, Chicago, USA. N. Dethlefs, H. Hastie, H. Cuayáhuitl, and O. Lemon. 2013. Conditional Random Fields for Responsive Surface Realisation Using Global … Cited by 1 Related articles All 10 versions Cite Save More

14th Annual Meeting of the Special Interest Group on Discourse and Dialogue F Metz – 2013 – sigdial.org … 384 Which ASR should I choose for my dialogue system? … 452 Dialog State Tracking using Conditional Random Fields Hang Ren, Weiqun Xu, Yan Zhang and Yonghong Yan . . . . . … All 7 versions Cite Save More

TechWare: Spoken Language Understanding Resources [Best of the Web] G Tur, YY Wang, D Hakkani-Tur – Signal Processing Magazine, …, 2013 – ieeexplore.ieee.org … Identifier 10.1109/MSP.2013.2241313 Date of publication: 5 April 2013 [FIG1] A conceptual architecture of a spoken dialog system. … and employing corre- sponding statistical techniques such as hidden Markov model (HMM) or more recently conditional random fields (CRFs) [eg … Related articles All 12 versions Cite Save

HRI-2013 workshop on probabilistic approaches for robot control in human-robot interaction (PARC-HRI) A Atrash, R Mead – Proceedings of the 8th ACM/IEEE international …, 2013 – dl.acm.org … as for predicting transitions into, during, and out of social interactions based on human spatial dynamics [2]. Conditional Random Fields have been … Q. Cai, J. Mao, and B. Guo, “Planning and acting under uncertainty: A new model for spoken dialogue systems,” in Uncertainty in … Related articles All 4 versions Cite Save

Towards a Truly Statistical Natural Language Generator O Dušek – 2013 – ufal.ms.mff.cuni.cz … Natural language generation as planning under uncertainty for spoken dialogue systems. EMNLP SimpleNLG Gatt, A. and Reiter, E. 2009. … 2009. Natural Language Generation with Tree Conditional Random Fields. EMNLP WASP?1 Wong, YW and Mooney, RJ 2007. … Related articles All 3 versions Cite Save More

Discriminative framework for spoken tunisian dialect understanding M Graja, M Jaoua, LH Belguith – Statistical Language and Speech …, 2013 – Springer … To perform semantic labeling, many statistical methods have been used, from ge- nerative to discriminative models [2]. Conditional random fields (CRF) model … Despite the importance of semantic analysis for the implementation of any dialogue system, there are only a few works … Related articles All 3 versions Cite Save

Exploiting Shared Information for Multi-Intent Natural Language Sentence Classification P Xu, R Sarikaya – 2013 – old-site.clsp.jhu.edu … 1. Introduction In spoken dialogue systems, understanding the user’s intent is a crucial step for the success of human-computer interaction. The … 13]. These models are gener- ally described as hidden conditional random fields. 4.2. … Related articles All 4 versions Cite Save More

Learning Dialogue Management Models for Task-Oriented Dialogue with Parallel Dialogue and Task Streams EY Ha, CM Mitchell, KE Boyer, JC Lester – sigdial.org … reinforcement learning typically requires a very large set of training da- ta, which limits the complexity of the dialogue system in its … models (Bangalore et al., 2008; Sridhar et al., 2009; Ha et al., 2012), support vector machines (Ivanovic, 2008), conditional random fields (Kim et al … Related articles All 10 versions Cite Save More

Dialogue Act Recognition from Audio and Transcription of Human-Human Conversations N Ramachandran – ijcttjournal.org … II. RELATED WORK Because of the importance of dialogue act classification within dialogue systems, it has been an active … A recently proposed alternative approach uses a discriminative approach, namely Conditional Random Fields (CRFs), [4] to simultaneously segment an … Related articles All 2 versions Cite Save More

User Goal Change Model for Spoken Dialog State Tracking Y Ma – NAACL HLT SRW 2013 – aclweb.org … A conversational movie search system based on conditional random fields. In INTERSPEECH. … Efficient probabilistic track- ing of user goal and dialog history for spoken dialog systems. In Twelfth Annual Conference of the Interna- tional Speech Communication Association. … Cited by 1 Related articles All 5 versions Cite Save More

Fuzzy Matching of Semantic Class in Chinese Spoken Language Understanding LI Yanling, Z Qingwei… – IEICE TRANSACTIONS on …, 2013 – search.ieice.org … key words: fuzzy matching, Conditional Random Field (CRF), Spoken Lan- guage Understanding (SLU), Named Entity Recognition (NER), similarity … 1]. With the improvement of Automatic Speech Recognition (ASR), the technology of spoken dialog systems has developed … Related articles All 4 versions Cite Save

Prediction of Visual Backchannels in the Absence of Visual Context Using Mutual Influence D Ozkan, LP Morency – Intelligent Virtual Agents, 2013 – Springer … [10] showed that Conditional Random Field models can be used to learn predictive features of backchannel feedback. … Each expert conditional distribution is defined by P?(y|x,??) using the usual conditional random field formulation: … Related articles All 3 versions Cite Save

Query understanding enhanced by hierarchical parsing structures J Liu, P Pasupat, Y Wang, S Cyphers… – … (ASRU), 2013 IEEE …, 2013 – ieeexplore.ieee.org … Semi-Markov Conditional Random Fields for Information Extraction. In Advances in Neural Information Processing Systems (NIPS), 2004. [20] J. Liu, P. Pasupat, S. Cyphers, and J. Glass. ASGARD: A Portable Architecture for Multilingual Dialogue Systems. In Proc. … Related articles All 4 versions Cite Save

Easy contextual intent prediction and slot detection A Bhargava, A Celikyilmaz… – … , Speech and Signal …, 2013 – ieeexplore.ieee.org … Using conditional random fields for slot detection, we find that incorporating features based on the appearance of slots in previous utterances yields no … Intents signify the goal of the user and vary across domains, but ultimately, a dialog system must at some point make a … Cited by 2 Related articles All 4 versions Cite Save

Sub-lexical Dialogue Act Classification in a Spoken Dialogue System Support for the Elderly with Cognitive Disabilities K Sadohara, H Kojima, T Narita, M Nihei, M Kamata… – aclweb.org … This paper presents a dialogue act classification for a spoken dialogue system that delivers necessary information to elderly subjects … 13], transformation-based learning [26], hidden Markov models (HMMs) [1], maximum entropy models [22], conditional random fields [27], and … Related articles All 7 versions Cite Save More

Dialogue System Theory B Thomson – Statistical Methods for Spoken Dialogue Management, 2013 – Springer … A simulated environment will often generate situations that the dialogue system designer will not have thought about and the system can … Levin and Pieraccini 1997 ), goal-based models (Pietquin and Renals 2002 ; Scheffler and Young 2001 ), conditional random fields (Jung et … Related articles All 2 versions Cite Save

Latent semantic modeling for slot filling in conversational understanding G Tur, A Celikyilmaz… – Acoustics, Speech and …, 2013 – ieeexplore.ieee.org … gains on seman- tic slot filling models when features from latent semantic models are used in a conditional random field (CRF). … More specifically, targeted SLU models in hu- man/machine spoken dialog systems aim to automatically identify several components: (i) the domain … Related articles All 7 versions Cite Save

Dialogue Act Recognition in Synchronous and Asynchronous Conversations M Tavafi, Y Mehdad, S Joty, G Carenini… – Proceedings of the …, 2013 – oldsite.aclweb.org … the human social intentions in spoken conversations and in many applications including summariza- tion (Murray, 2010), dialogue systems and di … algorithms, which in- clude SVM-multiclass and two structured predic- tors SVM-hmm and Conditional Random Fields (CRF) … Cited by 1 Related articles All 10 versions Cite Save More

Concept Discovery and Automatic Semantic Annotation for Language Understanding in an Information-Query Dialogue System Using Latent Dirichlet Allocation and … N Camelin, B Detienne, S Huet, D Quadri… – Knowledge Discovery, …, 2013 – Springer … To give a full description of the architecture of a dialogue system is out of the scope of this paper … decade: hidden Markov models, finite state transducers, maximum entropy Markov models, support vector machines, dynamic Bayesian networks and conditional random fields (CRF … Related articles All 2 versions Cite Save

IsNL? A Discriminative Approach to Detect Natural Language Like Queries for Conversational Understanding A Celikyilmaz, G Tur, D Hakkani-Tür – 2013 – research.microsoft.com … Only re- cently this relational but noisy data has been a valuable infor- mation source for building spoken dialog systems. … the state-of-the-art ap- proaches for slot filling [4, 5, among others], we use discrim- inative statistical models, namely conditional random fields, (CRFs) [15]. … Related articles All 6 versions Cite Save

Towards a Truly Statistical Natural Language Generator for Spoken Dialogues O Dušek – mff.cuni.cz … Lu, W., Ng, HT, and Lee, WS, Natural language generation with tree conditional random fields, in Proc. … Rieser, V. and Lemon, O., Natural language generation as planning under uncertainty for spoken dialogue systems, in Empirical methods in natural language generation, p … Related articles Cite Save More

Unsupervised Spoken Language Understanding for a Multi-domain Dialog System D Lee, M Jeong, K Kim, S Ryu, G Lee – 2013 – ieeexplore.ieee.org … In section IV, we explain the structure of a dialog system that uses the unsupervised SLU framework. In … context. Jeong et al. [27] introduced triangular chain conditional random fields, which can be applied to joint modeling, to solve the SLU problem. … Related articles Cite Save

Edit Distance Comparison Confidence Measure for Speech Recognition D Skurzok, B Zió?ko – Multimedia and Ubiquitous Engineering, 2013 – Springer … A relation to other, non-first hypothesis can provide it. It allows to repeat a question by a spoken dialogue system or choose a default answer for an unknown utterance. … Applying of conditional random fields was recently tested [10] for confidence estimation. … Related articles Cite Save

Language style and domain adaptation for cross-language SLU porting EA Stepanov, I Kashkarev, AO Bayer… – … (ASRU), 2013 IEEE …, 2013 – ieeexplore.ieee.org … In a live dialog system these entities are usually handled by their associated grammars, either handcrafted by the developers or provided as built-in by the ASR system. … One of the recent approaches to SLU is based on conditional random fields (CRF) [12]. … Related articles Cite Save

Incorporating semantic information to selection of web texts for language model of spoken dialogue system K Yoshino, S Mori, T Kawahara – Acoustics, Speech and Signal …, 2013 – ieeexplore.ieee.org … In this paper, we propose a semantic-level criterion to measure the relevance to the task domain of the spoken dialogue system. 4.1. … Alternatively, we can compute P(D|s) via a discriminative model such as Logistic Regression (LR) model and Conditional Random Fields (CRF). … Related articles All 4 versions Cite Save

Deploying speech interfaces to the masses A Pappu, A Rudnicky – Proceedings of the companion publication of the …, 2013 – dl.acm.org … S., Pasupat, P., McGraw, I., and Glass, J. A conversational movie search system based on conditional random fields. in Proc. of Interspeech 2012 (2012). 5. Raux, A., Langner, B., Bohus, D., Black, A., and Eskenazi, M. Lets go public! taking a spoken dialog system to the real … Related articles Cite Save

Interactive spoken content retrieval by extended query model and continuous state space Markov Decision Process TH Wen, H Lee, P Su, LS Lee – Acoustics, Speech and Signal …, 2013 – ieeexplore.ieee.org … [5] Jingjing Liu, Scott Cyphers, Panupong Pasupat, Ian McGraw, and Jim Glass, “A conversational movie search system based on conditional random field,” in Interspeech, 2012. … [8] Yi-cheng Pan and Lin-shan Lee, “Type-II dialogue systems for information access from … Related articles All 2 versions Cite Save

Generalization of discriminative approaches for speech language understanding in a multilingual context B Jabaian, F Lefèvre, L Besacier – Statistical Language and Speech …, 2013 – Springer … B., Besacier, L., Lef`evre, F.: Combination of stochastic understanding and machine translation systems for language portability of dialogue systems. … Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data … Related articles All 3 versions Cite Save

Multimodality and Dialogue Act Classification in the RoboHelper Project L Chen, B Di Eugenio – sigdial.org … We employ supervised learn- ing approaches, specifically: Conditional Random Field (CRF) (Lafferty et al., 2001), Maximum En- tropy (MaxEnt), Naive … However, dif- ferent from other sequence labeling problems such as part-of-speech tagging, a dialogue system can- not wait … Related articles All 7 versions Cite Save More

Barge-in effects in Bayesian dialogue act recognition and simulation H Cuayáhuitl, N Dethlefs, H Hastie… – … (ASRU), 2013 IEEE …, 2013 – ieeexplore.ieee.org … In this paper, we focus on user dialogue act recognition and user simulation for spoken dialogue systems at the se- mantic level. … Other graphical models for simulation have been used by [28], who compare different types of HMMs and [29] who use conditional random fields. … Cited by 1 Related articles All 3 versions Cite Save

Topic Independent Identification of Agreement and Disagreement in Social Media Dialogue A Misra, MA Walker – Evolution – aclweb.org … Topic Independent Identification of Agreement and Disagreement in Social Media Dialogue Amita Misra & Marilyn A. Walker Natural Language and Dialogue Systems Lab Computer Science Department University of California, Santa Cruz maw|amitamisra@soe.ucsc.edu … Cited by 1 Related articles All 7 versions Cite Save More

How Social Signal Processing (SSP) Can Help Assessment of Bonding Phenomena in Developmental Psychology? E Delaherche, S Boucenna, M Chetouani… – Neural Nets and …, 2013 – Springer … Various sequential learning mod- els, such as Hidden Markov Models (HMMs) or Conditional Random Fields (CRFs), are usually used to characterize … the prediction of turn-taking and back- channels has been largely studied in the perspective of building fluent dialog systems. … Related articles All 5 versions Cite Save

Identification of Speakers and Scenes from Movie Dialogue A Kundu – 2013 – dspace.jdvu.ac.in … 21 3.2.3.4 Conditional Random Field . . . . . … This corpus is aimed at training chat oriented dialog systems with the dialogue data. The Cornell Movie Dialogue Corpus (Danescu-Niculescu-Mizil and Lee, 2011) is yet … Related articles All 2 versions Cite Save

The Role of Context in Affective Behavior Understanding LP Morency – Social Emotions in Nature and Artifact, 2013 – books.google.com … Punctuation: We use punctuation features output by the dialogue system as a proxy for prosody cues. … Two of the most popular sequential models are the hidden Markov model (HMM)(Rabiner, 1989) and the conditional random field (CRF)(Lafferty et al., 2001). … Related articles All 2 versions Cite Save

PAL: A Chatterbot System for Answering Domain-specific Questions Y Liu, M Liu, X Wang, L Wang, J Li – ACL 2013, 2013 – Citeseer … System based on the Vector Space Model. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, Jeju, Republic of Korea, 8-14 July 2012. pages 37–42 Shilin Ding, Gao Cong, Chin-Yew Lin, Xiaoyan Zhu. Using Conditional Random Fields … Related articles All 7 versions Cite Save More

Audio Enhancement and Robustness B Schuller – Intelligent Audio Analysis, 2013 – Springer … In: André, E., Dybkjaer, L., Neumann, H., Pieraccini, R., Weber, M. (eds.) Perception in Multimodal Dialogue Systems: 4th IEEE Tutorial and Research Workshop on Perception and … Reiter, S., Schuller, B., Rigoll, G.:Hidden conditional random fields for meeting segmentation. … Related articles Cite Save

Detecting OOV Names in Arabic Handwritten Data J Chen, R Prasad, H Cao… – Document Analysis and …, 2013 – ieeexplore.ieee.org … 1455-1462, 2006. [13] H. Sun, G. Zhang, F. Zheng and M. Xu, “Using word confidence measure for oov words detection in a spontaneous spoken dialog system”. In Proc. … “Conditional random fields: Probabilistic models for segmenting and labeling sequence data”. In Proc. … Related articles All 2 versions Cite Save

Multi-style adaptive training for robust cross-lingual spoken language understanding X He, L Deng, D Hakkani-Tur… – Acoustics, Speech and …, 2013 – ieeexplore.ieee.org … “Combination of stochastic understanding and machine translation systems for language portability of dialogue systems,” in Proceedings of the … “Conditional random fields: Probabilistic models for segmenting and labeling sequence data,” in Proceedings of the ICML, 2001. … Cited by 3 Related articles All 8 versions Cite Save

Utterance Classification Using Linguistic and Non-linguistic Information for Network-Based Speech-to-Speech Translation Systems K Sugiura, R Lee, H Kashioka, K Zettsu… – … (MDM), 2013 IEEE …, 2013 – ieeexplore.ieee.org … A number of methods including conditional random fields (CRFs) and perceptrons are com- pared in [6]. The utterance classification of imbalanced data has a … [4] N. Reithinger and D. Sonntag, “An integration framework for a mobile multimodal dialogue system accessing the … Related articles All 4 versions Cite Save

Discriminative recognition rate estimation for n-best list and its application to n-best rescoring A Ogawa, T Hori, A Nakamura – Acoustics, Speech and Signal …, 2013 – ieeexplore.ieee.org … Spoken dialogue systems exploit N-best lists for dialogue modeling, eg [13, 14]. … 2.1. Extraction of N-best Word Alignment Features Our ETC is based on conditional random fields (CRF) [19], ie a discriminative model, and therefore, an important point to conduct 6832 … Cited by 2 Related articles All 2 versions Cite Save

Detection of nonverbal vocalizations using Gaussian Mixture Models: looking for fillers and laughter in conversational speech TF Krikke, KP Truong – 2013 – wwwhome.ewi.utwente.nl … One way to tackle these errors is to for example use Hidden Conditional Random Field techniques that can take into account both local … dynamic mod- elling for the recognition of non-verbal vocalisations in conver- sational speech,” Perception in multimodal dialogue systems, pp … Related articles All 3 versions Cite Save More

Natural Language Processing and Chinese Computing GZJ Li, DZY Feng – Springer … 19 Hongling Wang, Yonglei Zhang, and Guodong Zhou Chinese Negation and Speculation Detection with Conditional Random Fields….. … Lu, Yingmin Tang, Zhi Tang, Yujun Gao, and Jianguo Zhang Simulated Spoken Dialogue System Based on … Cite Save

Probabilistic Activity Recognition for Navigation O Font, G Frances, A Jonsson, P Bartie, W Mackaness – researchgate.net … Existing approaches to activity recognition using GPS sig- nals include hierarchical conditional random fields [1] and clustering to detect recurring patterns … shows the trajectory of a user in the Stockholm experiments, recorded during earlier work on spoken dialogue systems [11 … Related articles Cite Save More

[BOOK] Statistical methods for spoken dialogue management B Thomson – 2013 – books.google.com … In Proceedings of SLT, 2010. B. Thomson, J. Schatzmann, K. Weilhammer, H. Ye, and S. Young. Training a real—world POMDP-based dialog system. … B. Thomson, J. Schatzmann, and S. Young. Bayesian update of dialogue state for robust dialogue systems. … Cited by 24 Related articles All 5 versions Cite Save More

Theoretical analysis of diversity in an ensemble of automatic speech recognition systems K Audhkhasi, A Zavou, P Georgiou… – in IEEE Transactions on …, 2013 – sail.usc.edu … data set. Section IV describes our experimental setup using the Kaldi ASR toolkit [29] and ASR confidence estimation using a variety of lattice-based and prosodic features within a conditional random field (CRF) [30] model. We … Cited by 1 Related articles Cite Save More

Spoken language understanding and dialog: Case-frame based robust parser, semi-Markov conditional random field (CRF), boosted decision tree, rule-based or Markov decision process-based dialog management, and recurrent neural networks for sentence understanding The magazine archive includes every article published in Communications of the ACM for over the past 50 years. D Zhang – Communications of the ACM – cacm.acm.org

Hierarchical speech-act classification for discourse analysis S Kang, Y Ko, J Seo – Pattern Recognition Letters, 2013 – Elsevier … in dialogue systems. Thus, in our model, we employ a Support Vector Machine (SVM) (Vapnik, 1995), which has been widely used and has demonstrated significant performance in various learning tasks (Kim et al., 2011), since HMM and Conditional Random Fields (CRFs) are … Related articles All 4 versions Cite Save

Insight into Information Extraction Method using Natural Language Processing Technique K Dhanasekaran, R Rajeswari – Insight, 2013 – ijcsma.com … Jeremy Morris, and Eric Fosler-Lussier(2008) have presented that the conditional random fields (CRFs) are a statistical framework that has … language model adaptation using two speech recognition tasks: a medium vocabulary medical domain doctor-patient dialog system and a … Related articles All 3 versions Cite Save More

A Comparison of Evaluation Measures for Emotion Recognition in Dimensional Space R Jenke, A Peer, M Buss – Affective Computing and Intelligent …, 2013 – ieeexplore.ieee.org … and facial expressions in- clude Long Short-Term Memory (LSTM) Recurrent Neu- ral Networks and Conditional Random Fields [11] and … and J. Williams, “Emotion recognition using bio-sensors: First steps towards an automatic system,” in Affective Dialogue Systems, 2004, pp. … Related articles All 4 versions Cite Save

Semi-Supervised Semantic Tagging of Conversational Understanding using Markov Topic Regression A Celikyilmaz, D Hakkani-Tur, G Tur, R Sarikaya – oldsite.aclweb.org … It initially starts with training supervised Conditional Random Fields (CRF) (Lafferty et al., 2001) on the source train- ing data which has been semantically tagged. Us- ing the trained model, it decodes unlabeled dataset from the target domain. … Related articles All 10 versions Cite Save More

A Four-Participant Group Facilitation Framework for Conversational Robots Y Matsuyama, I Akiba, A Saito, T Kobayashi – oldsite.aclweb.org … able Markov decision process (POMDP), which is suit- able for real-world sequential decision processes, in- cluding dialogue systems (Williams and … Based on the proposed method by Nakagawa et al, we use linear-chain conditional random fields (CRF) for the IBO encoding. … Related articles All 7 versions Cite Save More

Generating More Specific Questions for Acquiring Attributes of Unknown Concepts from Users T Otsuka, K Komatani, S Sato, M Nakano – newdesign.aclweb.org … during dialogues. A word unknown to spoken dialogue systems can appear in user utterances, and systems should be ca- pable of acquiring information on it from the conversation partner as a kind of self- learning process. As … Cited by 1 Related articles All 8 versions Cite Save More

Large vocabulary continuous speech recognition based on WFST structured classifiers and deep bottleneck features Y Kubo, T Hori, A Nakamura – Acoustics, Speech and Signal …, 2013 – ieeexplore.ieee.org … is also promising since a WFST constitutes a common framework for several application fields such as speech summarization, speech translation, and dialogue systems. 7632 … [8] A. Gunawardana, M. Mahajan, A. Acero, and JC Platt, “Hidden conditional random fields for phone … Cited by 1 Related articles All 2 versions Cite Save

Bootstrapping Text-to-Speech for speech processing in languages without an orthography S Sitaram, S Palkar, YN Chen… – … , Speech and Signal …, 2013 – ieeexplore.ieee.org … Thus allowing spoken dialog systems, information giving systems, etc. to be easily developed without having to create, teach and enforce a new writing system. … [14] John Lafferty, Andrew McCallum, and Fernando Pereira, “Conditional Random Fields: Probabilistic Models for … Cited by 2 Related articles Cite Save

Identifying salient sub-utterance emotion dynamics using flexible units and estimates of affective flow EM Provost – … , Speech and Signal Processing (ICASSP), 2013 …, 2013 – ieeexplore.ieee.org … [7] J. Liscombe, G. Riccardi, and D. Hakkani-Tür, “Using context to improve emotion detection in spoken dialog systems,” in Interspeech, Sept. 2005, pp. … [9] EM Schmidt and YE Kim, “Modeling musical emotion dy- namics with conditional random fields,” ISMIR, Miami, FL, 2011. … Related articles All 3 versions Cite Save

A Survey of Listener Behavior and Listener Models for Embodied Conversational Agents E Bevacqua – Coverbal Synchrony in Human-Machine Interaction, 2013 – books.google.com … edited. When a discrepancy is found, a feedback utterance is generated. Nakano et al.(1999) developed a spoken dialogue system, called WIT, that enables robust utterance understanding and real-time listener’s responses. The … Related articles All 3 versions Cite Save

A Graph-based Cross-lingual Projection Approach for Spoken Language Understanding Portability to a New Language S Kim – 2013 – oar.a-star.edu.sg … Index Terms— Spoken Dialogue Systems, Spoken Lan- guage Understanding, Language Portability, Statistical Ma- chine Translation … We used maximum entropy (ME) and conditional random fields (CRF) models for DA identification and NE recogni- tion, respectively. … Related articles All 2 versions Cite Save

Predicate argument structure analysis using partially annotated corpora K Yoshino, S Mori, T Kawahara – Proc. of the Sixth International Joint …, 2013 – aclweb.org … 2008. Training conditional random fields using incomplete annotations. In Proc. COLING, pages 897–904. … 2011. Spoken dialogue system based on information ex- traction using similarity of predicate argument structures. In Proc. SIGDIAL, pages 59–66. … Cited by 2 Related articles All 8 versions Cite Save More

ConceptNet 5: A large semantic network for relational knowledge R Speer, C Havasi – The People’s Web Meets NLP, 2013 – Springer … Previous versions of ConceptNet [11] have been used, for example, to build a system for analyzing the emotional content of text [6], to create a dialog system for improving software specifications [14], to recognize activities of daily living [24], to visualize topics and trends in a … Cited by 9 Related articles Cite Save

Text to Speech in New Languages without a Standardized Orthography S Sitaram, GK Anumanchipalli, J Chiu… – Proceedings of 8th …, 2013 – parlikar.com … form to represent the speech to be generated, and produce a string of phones from the natural language generation model in the bus information dialog system. … For inducing word-like units, we used cross-lingual information to train a Conditional Random Field (CRF) model. … Cited by 1 Related articles All 3 versions Cite Save More

Kernel-Based Discriminative Re-ranking for Spoken Command Understanding in HRI R Basili, E Bastianelli, G Castellucci, D Nardi… – AI* IA 2013: Advances in …, 2013 – Springer … joint modeling of speech recognition and language understanding through a perceptron classifier is de- fined in a conversational dialogue system. … set of hypotheses gen- erated by local stochastic models, such as Stochastic Grammars (SGs) or Conditional Random Fields (CRF … Cited by 1 Related articles All 2 versions Cite Save

Structured Probabilistic Modelling for Dialogue Management P Lison – 2013 – opendial.googlecode.com … The ongoing research on spoken dialogue systems (SDS) is precisely trying to implement this ob- jective. A spoken dialogue system is a computer system able to converse with humans via everyday spoken language. … Figure 1.1: Schematic view of a spoken dialogue system. … Related articles All 2 versions Cite Save More

The Role of Affect Analysis in Dialogue Act Identification N Novielli, C Strapparava – 2013 – ieeexplore.ieee.org … is a large number of applications that could benefit from automatic DA annotation, such as dialogue systems, blog analysis … corpus has been used also in studies addressing simultaneous dialog act segmentation and classification using Conditional Random Fields using lexical … Related articles All 4 versions Cite Save

Human desire inference process and analysis J Dong – 2013 – lib.dr.iastate.edu … given the observations using Hidden Markov Model (HMM), Dynamic Bayesian Networks (DBNs) and Conditional Random Field (CRF) [9, 10]. The variants of CRF have been used to … dialog system to adjust the policy in providing instructions, based on the recognized time … Related articles Cite Save

On the dynamic adaptation of language models based on dialogue information JM Lucas-Cuesta, J Ferreiros, JD Echeverry… – Expert Systems with …, 2013 – Elsevier … In Spoken Language Dialogue Systems (SLDS), in which there are several interconnected modules, each one performing a different task (speech … of the identification of the most relevant words for each topic, those topics being obtained using Conditional Random Fields (CRFs … Cited by 3 Related articles All 7 versions Cite Save

Context-based counselor agent for software development ecosystem T Shinozaki, Y Yamamoto, S Tsuruta – Computing, 2013 – Springer Page 1. Computing DOI 10.1007/s00607-013-0352-y Context-based counselor agent for software development ecosystem Tetsuo Shinozaki · Yukiko Yamamoto · Setsuo Tsuruta Received: 6 February 2013 / Accepted: 24 September 2013 © Springer-Verlag Wien 2013 … Cited by 1 Related articles Cite Save

Controlling the Listener Response Rate of Virtual Agents I de Kok, D Heylen – Intelligent Virtual Agents, 2013 – Springer … [9]. This model is the “Consensus 2” model. It is a Conditional Random Fields model trained on the other 22 interactions from the MultiLis corpus. … Nishimura, R., Kitaoka, N., Nakagawa, S.: A spoken dialog system for chat-like conversations considering response timing. … Cited by 1 Related articles All 6 versions Cite Save

Speech-centric information processing: An optimization-oriented approach X He, L Deng – 2013 – ieeexplore.ieee.org … the output of SLU is further provided to a subsequent dialog control subsystem, a part of a spoken dialog system (open loop … of hidden Markov model (HMM) and composite HMM/context-free grammar (CFG) and conditional models/methods of conditional random field (CRF) and … Cited by 8 Related articles All 11 versions Cite Save

Kartik Audhkhasi is with the Signal Analysis and Interpretation Lab (SAIL) of the Electrical Engineering Department at the University of Southern California, Los … K Audhkhasi, AM Zavou, PG Georgiou, SS Narayanan – 2013 – ieeexplore.ieee.org … data set. Section IV describes our experimental setup using the Kaldi ASR toolkit [29] and ASR confidence estimation using a variety of lattice-based and prosodic features within a conditional random field (CRF) [30] model. We … Cite Save

An Investigation of Digital Reference Interviews: A Dialogue Act Approach K Inoue – 2013 – surface.syr.edu … a new aspect for evaluating digital reference services, 2) new data attributes for information extraction / retrieval algorithms (document models), and 3) a prototypical dialogue model for constructing fully-automated dialogue systems. 1.5 Summary … Related articles All 3 versions Cite Save

Exploiting multiple hypotheses for Multilingual Spoken Language Understanding M Calvo, F Garc?a, LF Hurtado, S Jiménez… – CoNLL- …, 2013 – oldsite.aclweb.org … How- ever, this is not a problem in most Spoken Dialog Systems since the semantic information to be ex- tracted is not very … This is the case of discriminative models (like Conditional Random Fields (Hahn et al., 2010)), and generative models (such as Hidden Markov Models … All 8 versions Cite Save More

Actor level emotion magnitude prediction in text and speech RA Calix, GM Knapp – Multimedia tools and applications, 2013 – Springer … In Tokuhisa et al. [24], the authors propose a model for detecting the emotional state of a user that interacts with a dialog system. … Mao et al. [18] conducted a study on the prediction of sentiment flow in documents using conditional random fields. … Cited by 4 Related articles All 8 versions Cite Save

Applying Context Respectful Summarization to Counseling Agent for the Japanese T Shinozaki, Y Ikegami, E Bissay… – … -Image Technology & …, 2013 – ieeexplore.ieee.org … [10] V. Hung, M. Elvir, A. Gonzalez, R. DeMara, “Towards a Method For Evaluating Naturalness in Conversational Dialog Systems,” Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics, 2008. … Related articles Cite Save

Improved recognition of Hungarian call center conversations B Tarjan, G Sarosi, T Fegyo… – Speech Technology and …, 2013 – ieeexplore.ieee.org … comparing the performance of three types of classifiers: Hidden Markov Models (HMM), Hidden Conditional Random Fields (HCRF), and … for the recognition of non-verbal vocalisations in conversational speech,” in Perception in multimodal dialogue systems, Springer Berlin … Related articles Cite Save

Machine learning paradigms for speech recognition: An overview L Deng, X Li – 2013 – ieeexplore.ieee.org Page 1. Copyright (c) 2013 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 16 Related articles All 9 versions Cite Save

Applications in Intelligent Speech Analysis B Schuller – Intelligent Audio Analysis, 2013 – Springer … In: André, E., Dybkjaer, L., Neumann, H., Pieraccini, R., Weber, M. (eds.) Perception in Multimodal Dialogue Systems: 4th IEEE Tutorial and Research Workshop on Perception and … 19(2), 313–330 (1993); Sha, F., Pereira, F.: Shallow parsing with conditional random fields. … Related articles Cite Save

Automatic Detection of Laughter and Fillers in Spontaneous Mobile Phone Conversations H Salamin, A Polychroniou… – Systems, Man, and …, 2013 – ieeexplore.ieee.org … The authors investigate three models: Hidden Markov Models, Hidden Conditional Random Fields (hCRF) and SVM … G. Rigoll, “Static and dynamic modelling for the recognition of non-verbal vocalisations in conversational speech,” in Perception in multimodal dialogue systems. … Related articles All 2 versions Cite Save

Domain-And Language-Adaptive Natural Language Controlling Framework P Barabás, J Szigeti, L Cser, I Juhász – 193.6.1.94 … Protocol JSON JavaScript Object Notation KQML Knowledge Query and Manipulation Language LCRF Linear-Conditional Random Field LG Link … Logical Form RDF Resource Description Framework SDK Software Development Kit SDS Speech Dialog System SNLP Stanford … Related articles All 4 versions Cite Save More

[BOOK] Man-machine Dialogue: Design and Challenges F Landragin – 2013 – books.google.com … 46 Chapter 3. The Development Stages of a Dialogue System . . . . . 47 3.1. Comparing a few development progresses . . . . . … 138 8.2.3. Dialogue management and multimodality management . . . 143 8.2.4. Can a dialogue system lie? . . . . … Related articles All 4 versions Cite Save More

Confidence Estimation for Automatic Speech Recognition Hypotheses MS SEIGEL – mi.eng.cam.ac.uk … Te development and application of a principled, flexible framework using conditional random field (CRF) models for confidence estimation is … Tis is important for downstream applications (eg dialogue systems, keyterm detection) which make decisions based on these scores, as … Related articles Cite Save More

Hybrid video emotional tagging using users’ EEG and video content S Wang, Y Zhu, G Wu, Q Ji – Multimedia Tools and Applications, 2013 – Springer … video features to emotional tags are modeled by different machine learning methods, such as support vector machine [82], support vector regression [15], neural networks [81], hidden Markov model [72, 85, 86], dynamic Bayesian networks [5], conditional random fields [87], etc. … Cited by 1 Related articles All 3 versions Cite Save

Multi levels semantic architecture for multimodal interaction S Dourlens, A Ramdane-Cherif, E Monacelli – Applied intelligence, 2013 – Springer Page 1. Appl Intell DOI 10.1007/s10489-012-0387-3 Multi levels semantic architecture for multimodal interaction Sébastien Dourlens · Amar Ramdane-Cherif · Eric Monacelli © Springer Science+Business Media, LLC 2012 Abstract … Cited by 2 Related articles All 7 versions Cite Save

Using Social Agents to Explore Theories of Rapport and Emotional Resonance J Gratch, SH Kang, N Wang – Social Emotions in Nature and …, 2013 – books.google.com Page 193. 11 Using Social Agents to Explore Theories of Rapport and Emotional Resonance Jonathan Gratch, Sin-Hwa Kang, & Ning Wang Introduction Emotions are often described as momentary, even dis- crete, reactions to some specific event. … Related articles Cite Save

Joint uncertainty decoding for noise robust subspace Gaussian mixture models,” L Lu, K Chin, A Ghoshal, S Renals – IEEE Transactions on Audio, …, 2013 – cstr.ed.ac.uk … against full spaces: 1) less computer memory (94\% reduction), 2) faster learning (93\% faster convergence) and better performance (8.4\% less time steps and 7.7\% higher reward).}, categories = {reinforcement learning, spoken dialogue systems} } @inproceedings{hochberg … Cited by 4 Related articles All 5 versions Cite Save More

[BOOK] Intelligent Audio Analysis BW Schuller – 2013 – Springer Page 1. Signals and Communication Technology Intelligent Audio Analysis Björn W. Schuller Page 2. Signals and Communication Technology For further volumes: http://www.springer.com/ series/4748 Page 3. Björn W. Schuller Intelligent Audio Analysis 123 Page 4. … Related articles All 5 versions Cite Save More

Automatic Allophone Deriving for Korean Speech Recognition J Xu, Y Si, J Pan, Y Yan – Computational Intelligence and …, 2013 – ieeexplore.ieee.org … [10] Sakriani Sakti, Andrew Finch, Chiori Hori, Hideki Kashioka, Satoshi Nakamura, “Conditional Random Fields for Modeling Korean Pronunciation Variation,” Proceedings of the Paralinguistic Information and its Integration in Spoken Dialogue Systems Workshop 2011, Part 2 … Cite Save

Speech Recognition Technology: A Survey on Indian Languages G Hemakumar, P Punitha – ijisis.org Page 1. International Journal of Information Science and Intelligent System, Vol. 2, No.4, 2013 Speech Recognition Technology: A Survey on Indian Languages Hemakumar G. 1, ? , Punitha P. 2 1Department of Computer Science … Related articles All 2 versions Cite Save More

[BOOK] Hierarchical Neural Network Structures for Phoneme Recognition D Vasquez, R Gruhn, W Minker – 2013 – Springer … 41 3.5.2 Conditional Random Fields . . . . . 42 3.5.3 Articulatory Features . . . . . … In these tasks, a Spo- ken Dialog System is needed [Minker 04] where the ASR module plays an important role in the robustness of the system. … Related articles All 6 versions Cite Save

[BOOK] Representing Space in Cognition: Interrelations of behaviour, language, and formal models PARISA KORDJAMSHIDI, JOANA HOIS, MARTIJN VAN OTTERLO MF MOENS – Representing Space in Cognition: Interrelations of …, 2013 – books.google.com … extracted from the labelled sequences. A conditional random field model (CRF)(Lafferty et al., 2001) is used to tag single words in a sentence with the roles trajector, landmark, spatial_indicator, none. CRFs are instances of … All 2 versions Cite Save

Speech-to-speech translation to support medical interviews JASG Rodrigues – 2013 – repositorio.ul.pt Page 1. UNIVERSIDADE DE LISBOA Faculdade de Ciências Departamento de Informática SPEECH-TO-SPEECH TRANSLATION TO SUPPORT MEDICAL INTERVIEWS Jo˜ao Ant´onio Santos Gomes Rodrigues PROJETO MESTRADO EM ENGENHARIA INFORM´ATICA … Cite Save

Generating Descriptions for Images A Gupta – 2013 – web2py.iiit.ac.in … A Conditional Random Field (CRF) based model; whose nodes correspond to image entities (such as objects, attributes and preposi- tions); is used … have often been used for various practi- cal applications such as summarization [Zhou04] and dialogue systems [Channarukul03 … Related articles Cite Save More

Processing temporal information in unstructured documents FNQMC Costa – 2013 – repositorio.ul.pt Page 1. UNIVERSIDADE DE LISBOA FACULDADE DE CIÊNCIAS DEPARTAMENTO DE INFORMÁTICA Processing Temporal Information in Unstructured Documents Francisco Nuno Quintiliano Mendonça Carapeto Costa DOUTORAMENTO EM INFORMÁTICA … Cited by 4 Related articles All 3 versions Cite Save

Complex Aggregates In Natural Language Interface To Databases MA Gupta – 2013 – web2py.iiit.ac.in … Rajeev Sangal, in the field of Dialogue Systems by using Natural Language Processing (NLP) techniques. In a Dialogue System, a dialogue is established in NL between a human and a machine, leading to an exchange of information at both ends. … Cite Save More

A bottom-up modular search approach to large vocabulary continuous speech recognition SM Siniscalchi, T Svendsen… – Audio, Speech, and …, 2013 – ieeexplore.ieee.org … Conditional random fields (CRFs) [43] are a mathematical tool that can also be pursue joint optimization of independent features, and a recent CRF approach to LVCSR [44], [45] with a companion toolkit called SCARF [46] was developed for performing ASR with Page 4. … Cited by 10 Related articles All 2 versions Cite Save

Hand gesture production and gestural co-activation ATG Cruzata – 2013 – gupea.ub.gu.se … This could be thanks to the fact that “researchers, being aware of the important role that gestures play in communicative exchanges, are starting to integrate some of them in the development of dialogue systems endowed with embodied conversational agents, with the aim of … Related articles Cite Save

Web Corpus Construction R Schäfer, F Bildhauer – Synthesis Lectures on Human …, 2013 – morganclaypool.com … Data-Intensive Text Processing with MapReduce Jimmy Lin and Chris Dyer 2010 Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Page 7. v … Cited by 10 Related articles All 5 versions Cite Save More

Knowledge Acquisition from User Reviews for Interactive Question Answering N Konstantinova – 2013 – wlv.openrepository.com … CoreInfo – Core Information CRF – Conditional Random Fields DAARC – Discourse Anaphora and Anaphor Resolution Colloquium DIPRE – Dual Iterative Pattern Relation Expansion DM – Dialogue Manager DS – Dialogue System EAT – Expected Answer Type … Related articles All 2 versions Cite Save

An Information-Extraction Approach to Speech Processing: Analysis, Detection, Verification, and Recognition CH Lee, SM Siniscalchi – 2013 – ieeexplore.ieee.org Page 1. This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. INVITED PAPER An Information-Extraction Approach to Speech Processing: Analysis, Detection, Verification, and Recognition … Cited by 5 Related articles All 3 versions Cite Save

Semi-Supervised Learning and Domain Adaptation in Natural Language Processing A Søgaard – Synthesis Lectures on Human Language …, 2013 – morganclaypool.com … Data-Intensive Text Processing with MapReduce Jimmy Lin and Chris Dyer 2010 Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Page 7. v … Cited by 2 Related articles All 4 versions Cite Save More

Parasocial Consensus Sampling: Modeling Human Nonverbal Behaviors from Multiple Perspectives L Huang – 2013 – www-scf.usc.edu Page 1. Parasocial Consensus Sampling: Modeling Human Nonverbal Behaviors from Multiple Perspectives by Lixing Huang Dissertation Presented to the FACULTY OF THE USC GRADUATE SCHOOL UNIVERSITY OF SOUTHERN … Related articles All 2 versions Cite Save More

[BOOK] Listening heads IA Kok – 2013 – doc.utwente.nl … 125 Page 10. 1 Introduction One of the issues to address in research on spoken dialogue systems and embodied conversational agents is to take care that the system produces appropriate behavior when the person interacting with the system is speaking. … Related articles All 5 versions Cite Save

Learning Out-of-Vocabulary Words in Automatic Speech Recognition L Qin – 2013 – cs.cmu.edu … In the past decade, many algorithms had been studied and developed to improve the performance of ASR systems. Popular applications of ASR, such as voice search, voice control and spoken dialog system, etc., had also been widely used. … Related articles All 3 versions Cite Save More

Rapid Development of Language Resources M Grác – is.muni.cz Page 1. MASARYK UNIVERSITY FACULTY OF INFORMATICS }w¡¢£¤¥ &123456789@ACDEFGHIPQRS`ye| Rapid Development of Language Resources PHD THESIS Marek Grác Brno, Spring 2013 Page 2. Declaration … Cited by 1 Related articles Cite Save More

Distributional phrasal paraphrase generation for statistical machine translation Y Marton – ACM Transactions on Intelligent Systems and …, 2013 – dl.acm.org Page 1. 39 Distributional Phrasal Paraphrase Generation for Statistical Machine Translation YUVAL MARTON, University of Maryland, Columbia University, and IBM TJ Watson Research Center Paraphrase generation has been … Related articles Cite Save