## Perceptron & Dialog Systems 2015

Perceptron

Best Dialog System Classifiers

Learning from real users: Rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems PH Su, D Vandyke, M Gasic, D Kim, N Mrksic… – arXiv preprint arXiv: …, 2015 – arxiv.org … Index Terms: spoken dialogue systems, real users, reward pre- diction, dialogue success classification, neural network 1. Introduction … Finally, the resulting scalars are concatenated and feed into a standard multi-layer perceptron (MLP), which may consist of multiple layers. … Cited by 8 Related articles All 12 versions

Integration of word and semantic features for theme identification in telephone conversations Y Esteve, M Bouallegue, C Lailler, M Morchid… – … Dialog Systems and …, 2015 – Springer … (eds.), Natural Language Dialog Systems and Intelligent … The elements of matrix U and vector b1 are estimated by a multi-layer perceptron having vector X … were performed with the manual transcriptions (TRS) of the conversations using simple multi-layer perceptrons (MLP) with … Cited by 4 Related articles All 6 versions

Reinforcement learning in multi-party trading dialog T Hiraoka, K Georgila, E Nouri, D Traum… – Proceedings of the …, 2015 – aclweb.org … In RL, the policy’s goal is to maximize a reward function, which in traditional task-based dialog systems is user satisfaction or task completion (Walker et al., 1998). … NFQ: Neural fitted Q iteration (NFQ) uses a multi-layered perceptron as the Q-function approximator. … Cited by 1 Related articles All 14 versions

The Influence of Context on Dialogue Act Recognition E Ribeiro, R Ribeiro, DM de Matos – arXiv preprint arXiv:1506.00839, 2015 – arxiv.org … tion. Wright [8] used a Multi-Layer Perceptron (MLP) [23] with one hidden layer to achieve 62% accuracy on the DCIEM Map Task Corpus, using suprasegmen- … However, this is not useful for a dialogue system trying to identify the intention of its conversational … Cited by 3 Related articles All 4 versions

Weakly supervised slot tagging with partially labeled sequences from web search click logs YB Kim, M Jeong, K Stratos… – Proceedings of the …, 2015 – msr-waypoint.com … 4.2 Experiments with CRF Variants Our main contribution is to leverage search log data to improve slot tagging in spoken dialogue systems. … Table 3: The F1 performance of variants of CRF across three domains, test on log data average perceptron. … Cited by 4 Related articles All 12 versions

Combining Several User Models to Improve and Adapt the Dialog Management Process in Spoken Dialog Systems D Griol, JM Molina, A Sanchis, Z Callejas – International Workshop on …, 2015 – Springer … From our previous work on dialog management [3], we propose the use of a multilayer perceptron for the classification, where the input layer … We have applied our user-adaptation methodology to develop and evaluate an adaptive dialog system for a travel-planning domain. … Related articles

A proposal for improving spoken dialog systems using context information fusion I Chairi, D Griol, J García… – Information Fusion (Fusion …, 2015 – ieeexplore.ieee.org … The spoken dialog system considers the concepts and values for the attributes provided by the user throughout the previous history of the dialog to … The best results were obtained using a multilayer perceptron (MLP) [37], where the input layer holds the codification of the dialog … Related articles

Discovering the Dialog Rules by Means of a Soft Computing Approach D Griol, JM Molina – 10th International Conference on Soft Computing …, 2015 – Springer … The WOz technique [11] allows the acquisition of a dialog corpus with real users without having a complete dialog system, for which the … In this work, we have used three approaches for the definition of the classification function: a multilayer perceptron (MLP), a multinomial naive … Related articles All 3 versions

An Ensemble-Based Classification Approach to Model Human-Machine Dialogs D Griol, AS de Miguel – Conference of the Spanish Association for Artificial …, 2015 – Springer … techniques, and a classifier based on artificial neural networks [4]. The best results were obtained using a multilayer perceptron (MLP) [1 … practical implementation of the proposed dialog management technique and its interaction with the rest of the modules in the dialog system. … Related articles

Response Generation in Dialogue using a Tailored PCFG Parser CYXWQ He – ENLG 2015, 2015 – aclweb.org … 2009. Natural Lan- guage Generation as Planning Under Uncertainty for Spoken Dialogue Systems. In Proceedings of the 12th Conference of the European Chapter of the A- CL, pp. … Michael White and Rajakrishnan Rajkumar. 2009. Perceptron Reranking for CCG Realization. … Related articles All 7 versions

Modeling Human-Machine Interaction by Means of a Sample Selection Method I Chairi, D Griol, JM Molina – … on Practical Applications of Agents and Multi- …, 2015 – Springer … Proc. Syst. 4, 1001–1008 (1992). 4. Ohnishi, N., Okamoto, A., Sugi, N.: Selective presentation of learning samples for efficient learning in multilayer perceptron. … Griol, D., Hurtado, L., Segarra, E., Sanchis, E.: A statistical approach to spoken dialog systems design and evaluation. … Related articles

Opportunities and obligations to take turns in collaborative multi-party human-robot interaction M Johansson, G Skantze – 16th Annual Meeting of the Special Interest …, 2015 – aclweb.org … The logged utterances from the dialogue system were then added as a third track of IPUs. … For this we explore the RIPPER (JRIP), Support Vector Machine (SVM) with linear kernel func- tion and Multilayer Perceptron (MLP) classifiers I think so too Yeah What about you? … Cited by 3 Related articles All 14 versions

Towards Emotionally Sensitive Conversational Interfaces for E-therapy D Griol, JM Molina, Z Callejas – … Work-Conference on the Interplay Between …, 2015 – Springer … This is the case of most spoken dialog systems, in which a baseline algorithm which always chooses “neutral” would have a very high … Once we have obtained the normalized features, we classify the corresponding utterance with a multilayer perceptron (MLP) into two categories … Related articles

Modeling users emotional state for an enhanced human-machine interaction D Griol, JM Molina – … Conference on Hybrid Artificial Intelligence Systems, 2015 – Springer … This is the case of most information providing spoken dialog systems, in which a baseline algorithm which always chooses “neutral” would have … Once we have obtained the normalized features, we classify the corresponding utterance with a multilayer perceptron (MLP) into two … Cited by 2 Related articles

User Modeling Optimization for the Conversational Human-Machine Interfaces D Griol, JM Molina – 10th International Conference on Soft Computing …, 2015 – Springer … As described in [7, 8], this approach is well-documented [9] and has been used to develop hundreds of successful commercial dialog systems. … A_{i},\mathcal {O}) \end{aligned}. As in our work on dialog management [15], we propose the use of a multilayer perceptron (MLP) to … Related articles All 3 versions

A Study of the 3D Sphere Wave Database Computing Model J Lee, Y Chang – International Information Institute (Tokyo). …, 2015 – search.proquest.com … Key Words: 3d database model, 12-PAC, spherical wave, perceptron, Plutchik-Wheel. … For instance, when conventional users used dialog system, which is based on natural language processing in smart devices, it gave the most similar answers to users’ question which was … Related articles All 2 versions

Interaction quality: assessing the quality of ongoing spoken dialog interaction by experts—and how it relates to user satisfaction A Schmitt, S Ultes – Speech Communication, 2015 – Elsevier … employed classification and regression trees (CART) and multilayer perceptrons (MLP … that real users may interpret the questions from the user survey differently while expert raters are expected to deliver a more stable rating when evaluating the performance of a dialog system. … Cited by 4 Related articles All 4 versions

Multicriteria neural network design in the speech-based emotion recognition problem C Brester, E Semenkin, M Sidorov… – Informatics in Control, …, 2015 – ieeexplore.ieee.org … we introduce the two-criterion optimization model to design multilayer perceptrons taking into … emotion recognition problem in the framework of intellectual spoken dialogue systems and, therefore … In the experiments conducted a multilayer perceptron (MLP) with one hidden layer … Related articles

Answer Extraction for Question Answering Game Application DD Putra, V Petukhova, D Klakow – ltc.amu.edu.pl … We aim at building an end-to-end Question Answer- ing Dialogue System (QADS) that provides an interactive guessing game where … 8We used two CRF implementations from CRF++9 and CRFsuite (Okazaki, 2007) with Averaged Perceptron (AP) and Limited-memory BFGS (L … Related articles All 2 versions

A comparative study of neural network models for lexical intent classification S Ravuri, A Stoicke – 2015 IEEE Workshop on Automatic …, 2015 – ieeexplore.ieee.org … 1. INTRODUCTION Utterance classification is an important pre-processing step for many dialog systems that interpret speech input. … Word embed- dings from those words, v1, v2, are stacked into a single vec- tor, which serves as input to a multilayer perceptron. … Cited by 1 Related articles All 4 versions

Evolutionary feature selection for emotion recognition in multilingual speech analysis C Brester, E Semenkin, I Kovalev… – 2015 IEEE Congress …, 2015 – ieeexplore.ieee.org … for all of the corpora [3]. Therefore, we combined the developed filter technique with the ensemble of classifiers (Multilayer Perceptron, Support Vector … A. Problem Definition One of the obvious ways to improve the intellectual abilities of spoken dialogue systems is related to their … Cited by 3 Related articles

ARS METAPLASTICA: A Cyber Metadiscipline of Creativity and Innovation between Science-Art-Design G Mura – 2015 International Conference on Cyberworlds (CW), 2015 – ieeexplore.ieee.org … Contact”} Q={threshold 0.8 Sensing:Form{0.4 0.35 0.2},Appearance(0.65); Feeling:Form{0.2 0.7 0.4},Appearance(0.85); Acting: f sendmessage(from RBS.C to RBS.H); } s=Sensing state of the Dialog system; ={Proximity f(x … [27] ML Minsky, S. Papert,Perceptrons:an Introduction to … Related articles All 2 versions

Identifying Various Kinds of Event Mentions in K-Parser Output A Sharma, NH Vo, S Aditya… – Proceedings of the 3rd …, 2015 – anthology.aclweb.org … Second, we developed a multi-class multilayer perceptron classifier to disambiguate dif- ferent senses of prepositions and assign the semantic relations appropriately. … 2007. Deep linguistic processing for spoken dialogue systems. … Cited by 1 Related articles All 13 versions

Building memory with concept learning capabilities from large-scale knowledge base J Shi, J Zhu – arXiv preprint arXiv:1512.01173, 2015 – arxiv.org … or more specifically, to learn what a certain name used by human means, is obviously highly useful, particularly in a KB-based dialog system. … We explore two kinds of neural network architectures for the concept learn- ing module, including multi-layer perceptrons (MLP) and … Cited by 2 Related articles All 4 versions

Machine Learning for Language Processing Lecture 1: Classification S Clark – 2015 – cl.cam.ac.uk … In 1969, Minsky and Papert published Percep- trons, which was a criticism of Rosenblatt’s perceptron (a simple form of neural network), arguing for … Here, the problem is to learn a dialogue system which knows how to respond to utterances from the user, for example in order to … Related articles

The MetaPlastic Technè: Cyber Art and Design Innovations G Mura – Analyzing Art, Culture, and Design in the Digital Age, 2015 – books.google.com … C to RBS. H);} s= Sensing state of the Dialog system; ?={Proximity f (x)= f (Interactor. position-System Threshold} RBS={C messages. p 1.0 P 0.3 0.10. … Canada: McGraw-Hill. Minsky, ML, & Papert, S.(1969). Perceptrons: an Introduction to Computational Geometry. MIT Press. … Related articles All 2 versions

Fusion of sentiment analysis and emotion recognition to model the user’s emotional state D Griol, JM Molina… – Information Fusion (Fusion …, 2015 – ieeexplore.ieee.org … This is the case of most spoken dialog systems, in which a baseline algorithm which always chooses “neutral” would have a very … Once we have obtained the normalized features, we clas- sify the corresponding utterance with a multilayer perceptron (MLP) into two categories … Related articles

Measuring the differences between human-human and human-machine dialogs D Griol, J Molina – 2015 – gredos.usal.es … From our previous work on dialog management (Griol et al., 2014), we propose the use of a multilayer perceptron for the classification, where the input layer receives the current state of the dialog, which is represented … 5. Case application: The Facilisimo spoken dialog system …

Multi-room speech activity detection using a distributed microphone network in domestic environments P Giannoulis, A Brutti, M Matassoni… – … 2015 23rd European, 2015 – ieeexplore.ieee.org … to far-field ASR in multi-room environ- ments, specifically showing the crucial impact of SAD in a multi- microphone spoken dialogue system. … We also consider the system of [18], which, instead of GMMs, employs multi-layer perceptron (MLP) models, followed by a finite state … Cited by 1 Related articles All 5 versions

Performance Analysis of FFNN-Based Language Model in Contrast with n-Gram KH Kim, D Lee, M Lim, M Ryang, GJ Jang… – … Dialog Systems and …, 2015 – Springer … Springer International Publishing Switzerland 2015 G. Geunbae Lee et al. (eds.), Natural Language Dialog Systems and Intelligent Assistants, DOI 10.1007/978-3-319-19291-8_25 253 … FFNN structure using multilayer perceptron (Bishop 1995) was proposed in Bengio et al. … Related articles All 3 versions

Romanian phonetic transcription dictionary for speeding up language technology development J Domokos, O Buza, G Toderean – Language Resources and Evaluation, 2015 – Springer … The used neural networks are totally connected MLP (multilayer perceptron) with two hidden layers. … Spontaneous speech recognition for Romanian in spoken dialogue systems. Proceedings of the Romanian Academy, 11 Series A(1), 8391. … Cited by 2 Related articles All 5 versions

Word embeddings combination and neural networks for robustness in asr error detection S Ghannay, Y Esteve, N Camelin – … (EUSIPCO), 2015 23rd …, 2015 – ieeexplore.ieee.org … for the two right words (R). Each feature vector is used separately in order to train a multilayer perceptron (MLP) with a … of word and semantic features for theme identification in telephone conversations,” in 6th International Work- shop on Spoken Dialog Systems (IWSDS 2015 … Cited by 3 Related articles All 3 versions

Semantic Role Labeling Improves Incremental Parsing I Konstas, F Keller – homepages.inf.ed.ac.uk … machine translation (Schwartz et al., 2011; Tan et al., 2011), reading time modeling (Demberg and Keller, 2008), or dialogue systems (Stoness et … the averaged structured percep- tron algorithm of Collins (2002); we give the pseu- docode in Algorithm 1. The perceptron makes T … Related articles All 7 versions

Resolving Discourse-Deictic Pronouns: A Two-Stage Approach to Do It SK Jauhar, RD Guerra, EG Pellicer, M Recasens – 2015 – research.google.com … is a central problem in Nat- ural Language Processing with a broad range of ap- plications such as summarization (Steinberger et al., 2007), textual entailment (Mirkin et al., 2010), in- formation extraction (McCarthy and Lehnert, 1995), and dialogue systems (Strube and Müller … Cited by 1 Related articles All 9 versions

Interactive Facial Expression Reader and Extension to First Impression Improver T Yamazaki, K Maehara, K Enomoto – Proceedings of the 2nd …, 2015 – dl.acm.org … Or, computer-based dialogue systems that make use of non-verbal information efficiently are encouraged to realize soon in near future. … [3] Zhang, Z. 1999. Feature-based facial expression recognition: Sensitivity analysis and experiments with a multi-layer perceptron. … Related articles

Edinburgh Research Explorer DPS Parsing – pdfs.semanticscholar.org … machine translation (Schwartz et al., 2011; Tan et al., 2011), reading time modeling (Demberg and Keller, 2008), or dialogue systems (Stoness et … the averaged structured percep- tron algorithm of Collins (2002); we give the pseu- docode in Algorithm 1. The perceptron makes T … Related articles All 2 versions

A Natural Language Query Builder Interface for Structured Databases Using Dependency Parsing R Kokare, K Wanjale – IJMSC-International Journal of Mathematical …, 2015 – mecs-press.org … Limitations of this approach are firstly, average perceptron to learn the feature weights of the joint models are used, which equally treats the POS and syntactic features. Training procedures should be better in this case. … This system is applied for spoken dialogue system. … Related articles

A proposal for the development of adaptive spoken interfaces to access the Web D Griol, JM Molina, Z Callejas – Neurocomputing, 2015 – Elsevier … The best results were obtained using a multilayer perceptron (MLP) [82]. … 3. Proposed framework to develop adaptive spoken dialog systems. Fig. 1 shows the architecture that integrates our proposed framework to generate adaptive spoken dialog systems. … Related articles All 3 versions

Incremental Semantic Construction Using Normal Form CCG Derivation Y Kato, S Matsubara – Lexical and Computational Semantics (* SEM …, 2015 – aclweb.org … Michael Collins and Brian Roark. 2004. Incremental parsing with the perceptron algorithm. … Andreas Peldszus and David Schlangen. 2012. Incre- mental construction of robust but deep semantic rep- resentations for use in responsive dialogue systems. … Related articles All 7 versions

Telugu dependency parsing using different statistical parsers BVS Kumari, RR Rao – Journal of King Saud University-Computer and …, 2015 – Elsevier … Parsing is useful in major NLP applications like Machine Translation, Dialogue Systems, Question Answering, etc. This led to the development of grammar-driven, data-driven and hybrid parsers. … Averaged perceptron (Collins, 2002) is used for learning. … Related articles

New transfer learning techniques for disparate label sets YB Kim, K Stratos, R Sarikaya, M Jeong – ACL. Association for …, 2015 – aclweb.org … This allows for efficient inference with HUCRFs de- spite their richness (see Maaten et al. (2011) for details). We use a perceptron-style algorithm of Maaten et al. (2011) for training HUCRFs. 4 Transfer learning between domains with different label sets … Cited by 7 Related articles All 9 versions

A system for recognizing human emotions based on speech analysis and facial feature extraction: applications to Human-Robot Interaction M Rabiei – 2015 – dspace-uniud.cineca.it … 1]. Speech emotion recognition has also been used in call center applications and mobile communication [2]. Some works tried to incorporate spoken dialogue system technology and service robots. Psychologists believe that … Related articles All 2 versions

Which ASR errors are hard to detect S Ghannay, N Camelin, Y Esteve – Errors by Humans and …, 2015 – errare2015.racai.ro … for the two right words (R). Each feature vector is used separately in or- der to train a multilayer perceptron (MLP) with a … of word and semantic features for theme identification in telephone conversa- tions,” in 6th International Workshop on Spoken Dialog Systems (IWSDS 2015 … Cited by 2 Related articles All 2 versions

Automatic Speech Recognition of Urdu Digits with Optimal Classification Approach H Ali, A Jianwei, K Iqbal – International Journal of Computer …, 2015 – search.proquest.com … et al [8] have reported the use of a multilayer perceptrons (MLP) for Urdu digits ASR … F. Gao, R. Guo, and R.-Z. Lu, STIS: a Chinese spoken dialogue system about Shanghai … 8] A. Ahad, A. Fayyaz, and T. Mehmood, Speech recognition using multilayer perceptron, in Proceedings. … Related articles All 5 versions

Emotion and Disposition Detection in Medical Machines: Chances and Challenges K Hartmann, I Siegert, D Prylipko – Machine Medical Ethics, 2015 – Springer … Typical classification methods for static (or turn-level) analysis are support vector machines (SVM) [20], multilayer perceptrons (or other types of neural … Callejas Z, López-Cózar R (2008) Influence of contextual information in emotion annotation for spoken dialogue systems. … Related articles All 8 versions

Automatic Speech Recognition-A Literature Survey on Indian languages and Ground Work for Isolated Kannada Digit Recognition using MFCC and ANN SB Harisha, S Amarappa, DSV Sathyanarayana – International Journal of … – eslibrary.org … Aggarwal, RK et al. (2011) [45] presented a novel approach by using multilayer perceptrons optimized with the help of genetic algorithm. … (2006) [108] presented an inexpensive approach for gathering the linguistic resources needed to power a simple spoken dialog system. … Cited by 2 Related articles All 2 versions

Emotion recognition based on EEG changes in movie viewing S Liu, J Meng, D Zhang, J Yang, X Zhao… – 2015 7th …, 2015 – ieeexplore.ieee.org … Using Bayesian weighted-log-posterior function and perceptron convergence algorithm, Yoo et al. … [4] A. Haag, S. Goronzy, P. Schaich, and J. Williams, “Emotion recognition using bio-sensors: First steps towards an automatic system,” in Affective dialogue systems, ed: Springer … Related articles

Big Data–Driven Natural Language–Processing Research and Applications V Gudivada, D Rao, V Raghavan – Big Data Analytics, 2015 – books.google.com … These results are used in other tasks such as co-reference resolution, word-sense disambiguation, semantic parsing, question answering, dialog systems, textual entailment, information extraction, information retrieval, and text summarization. … Cited by 3 Related articles

A New SVM Kernel for Keyword Spotting Using Confidence Measures Y Ben Ayed – International Journal on Artificial Intelligence Tools, 2015 – World Scientific … automatic speech recognition applications include dialogue systems, speech based interfaces and voice controlled systems which can be found in automatic applica … First, we use a Multi-Layer Perceptron (MLP), 28 known as the most used method for supervised classification. … Related articles

Improving Indian Language Dependency Parsing by Combining Transition-based and Graph-based Parsers BVS Kumari, RR Rao – International Journal of Computer …, 2015 – search.proquest.com … Parsing is useful in major NLP applications like Machine Translation, Dialogue systems, text generation, word sense disambiguation etc. … (2010) used a transition based dependency shift reduce parser (DeSR parser) that uses a Multilayer Perceptron (MLP) classifier with a … Related articles All 6 versions

Chinese Word POS Tagging with Markov Logic Z Liao, Q Zeng, Q Wang – Pacific-Asia Workshop on Intelligence and …, 2015 – Springer … The research on word POS tagging is of crucial importance for discourse and dialog systems, machine translation, information retrieval, information … used a general statistical framework that consists of a global linear model, trained by the generalized perceptron together with a … Related articles All 4 versions

Automatic recognition of prosodic patterns in semantic verbal fluency tests-an animal naming task for edutainment applications H Moniz, A Pompili, F Batista, I Trancoso… – 18TH …, 2015 – researchgate.net … The use of prosodic features can help predict more accurately cor- rectly recognized turns in dialogue systems [13], rather than the use of … Phone-based segmentation is provided by a phone recognizer, which is based on the Audimus Multilayer Perceptron (MLP) outputs[1]. The … Cited by 1 Related articles All 3 versions

SENSEI Coordinator M Kabadjov, EA Stepanov, F Celli, SA Chowdhury… – sensei-conversation.eu … HGI Harvard General Inquirer lexicon JRC Joint Research Centre of the European Commission MLP Multi-layer Perceptron MPQA Multi … of applications of DA analysis is quite wide and includes conversa- tion summarization (both spoken and written), dialogue systems, etc.; and … Related articles

Effects of feature type, learning algorithm and speaking style for depression detection from speech V Mitra, E Shriberg – 2015 IEEE International Conference on …, 2015 – ieeexplore.ieee.org … recognition toolkit,” in Proc. ASRU, 2011. [33] E. Shriberg, A. Stolcke, S. Ravuri, “Addressee Detection for Dialog Systems Using Temporal and Spectral Dimensions of Speaking Style,” Proc. of Interspeech, 2013. [34] V. Mitra … Cited by 2 Related articles All 4 versions

Self-Configuring Ensemble of Neural Network Classifiers for Emotion Recognition in the Intelligent Human-Machine Interaction E Sopov, I Ivanov – Computational Intelligence, 2015 IEEE …, 2015 – ieeexplore.ieee.org … Much research has been done on building intelligent dialogue systems (DS) that are able to collect this kind of information. … Several decision-level data integration techniques were used: averaged predictions, SVM and multi-layer perceptron (MLP) aggregation techniques, and … Related articles

A hybrid approach to pronominal anaphora resolution in Arabic A Abolohom, N Omar – Journal of Computer Science, 2015 – search.proquest.com … including machine translation, question-answer systems, text summarization or automatic abstracting, information extraction, language generation and dialog systems. … A number of the classifiers used include SVM, Multilayer Perceptron, NB, k-NN, Random Forest (RF), NB-Tree … Related articles All 4 versions

An empirical investigation to examine the usability issues of using adaptive, adaptable, and mixed-initiative approaches in in-teractive systems M Alshumari – 2015 – dora.dmu.ac.uk Page 1. I Online English Vocabulary Learning on Different Systems for Non-English Speakers Alshumari Mansour PhD 2015 Page 2. II Online English Vocabulary Learning on Different Systems for Non-English Speakers An … Related articles All 4 versions

Ellipsis R KEMPSON, R CANN… – The Handbook of …, 2015 – books.google.com Page 129. Trim size: 170mm x 244mm Lappin c04. tex V2-06/24/2015 10: 22 AM Page 114 4 Ellipsis RUTH KEMPSON, RONNIE CANN, ARASHESHGHI, ELENI GREGOROMICHELAKI, AND MATTHEW PURVER 1. Ellipsis: A Window on Context? … Related articles All 2 versions

Recognition of Facial Emotion through Face Analysis based on Quadratic Bezier Curves YH Lee, H Ahn, HJ Cho, JH Lee – Indian Journal of Science and …, 2015 – indjst.org … states. He used three different classifiers (multiple layer perceptron, adaptive neuro fuzzy inference and generic self-organizing fuzzy neural network), coupled with extracting features of Mel Frequency Cepstral coefficient. However … Cited by 2 Related articles

Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study M Sheikhan, M Abbasnezhad Arabi… – Connection …, 2015 – Taylor & Francis … Khanchandani, KB, & Hussain, MA (2009). Emotion recognition using multilayer perceptron and generalized feed forward neural network. … Enhancement of emotion detection in spoken dialogue systems by combining several information sources. … Related articles All 3 versions

Spoken term detection ALBAYZIN 2014 evaluation: overview, systems, results, and discussion J Tejedor, DT Toledano… – EURASIP …, 2015 – asmp.eurasipjournals.springeropen. … … The term detector employed word lattices obtained from an LVCSR system to output term detections. Next, the discriminative score normalization method relies on a multi-layer perceptron (MLP)-based confidence measure from two novel features. … Cited by 2 Related articles All 7 versions

A review of the role of sensors in mobile context-aware recommendation systems S Ilarri, R Hermoso, R Trillo-Lado… – International Journal of …, 2015 – dl.acm.org … infer the trans- portation means. Several classification algorithms are used to determine the transportation means: Bayesian network, decision tree, Random Forest, Na?ve Bayes, and Multilayer Perceptron. The authors report in … Related articles All 6 versions

Scalable Intelligence for Scheduling Systems BMA Cunha – 2015 – recipp.ipp.pt … 12 Figure 5 – Example of a graph containing stereotypes for religious people (Rich, 1979b)…. 22 Figure 6 – Representation of a multilayer perceptron with an hidden layer (O’Connor et al., 2012) …. … Related articles All 2 versions

Affect detection from non-stationary physiological data using ensemble classifiers O AlZoubi, D Fossati, S D’Mello, RA Calvo – Evolving Systems, 2015 – Springer Page 1. 1 3 Evolving Systems (2015) 6:79–92 DOI 10.1007/s12530-014-9123-z ORIGINAL PAPER Affect detection from non?stationary physiological data using ensemble classifiers Omar AlZoubi · Davide Fossati · Sidney D’Mello · Rafael A. Calvo … Cited by 6 Related articles All 4 versions

Data mining and machine learning in computational creativity H Toivonen, O Gross – Wiley Interdisciplinary Reviews: Data …, 2015 – Wiley Online Library … or to compose music[11] on the fly, or as a part of human–machine communication in dialog systems and conversational … PIERRE then learns multiple multilayer perceptrons on different levels of abstraction to model the relation between different recipes (essentially weighted … Cited by 1 Related articles All 7 versions

Bio-inspired hierarchical framework for multi-view face detection and pose estimation N McCarroll, A Belatreche, J Harkin… – 2015 International Joint …, 2015 – ieeexplore.ieee.org … outlined in section V. II. BIOINSPlRED ApPROACHES To F ACE DETECTION SNNs offer a more biologically plausible alternative to the classical McCulloch-Pitts perceptrons and rate-based neural networks. In SNNs the timing … Cited by 1 Related articles All 5 versions

Fuzzy Logic in Speech Technology-Introductory and Overviewing Glimpses HN Teodorescu – Fifty Years of Fuzzy Logic and its Applications, 2015 – Springer … The author claim that, although FL typically require computational-intensive algorithms, their method actually lowers the computation time. Pal and Mitra, in their early paper in (1992), analyzed the use of multilayer perceptrons and fuzzy sets in classification applications. … Related articles All 2 versions

TSVD as a Statistical Estimator in the Latent Semantic Analysis Paradigm G Pilato, G Vassallo – IEEE Transactions on Emerging Topics in …, 2015 – ieeexplore.ieee.org … Computing applications, such as natural language understanding, cognitive modeling, speech recog- nition, smart indexing, anti-spam filters, dialogue systems and other … Layer Perceptron (MLP) neural model [30], for which there is no a priori method for setting the number of … Cited by 1 Related articles All 4 versions

Fundamentals Tools of Modern Multilingual Speech Processing Technology in “Urdu” langauage Speech Processing MW Ashfaque, QN Naveed, SS Banu, QSSA Ahmed – ijaiem.org … According to past literature reviews, three applications including spoken dialogue systems, speech translation, and speaker recognition have been explored. It is noted that the speaker recognition issue is not particularly language-dependent. … Related articles

Modelling human emotion in interactive environments: Physiological ensemble and grounded approaches for synthetic agents PA Nogueira, R Rodrigues, E Oliveira… – Web …, 2015 – content.iospress.com … further benefiting from them (see Section 6.3). The selected classifiers were: decision trees, single-layer perceptron neural networks, random forests and support vector machines. Regarding decision trees, the splitting criterion … Related articles

Morpheme Segmentation and Concatenation Approaches for Uyghur LVCSR M Ablimit, T Kawahara, A Hamdulla – International Journal of Hybrid …, 2015 – sersc.org … Given all the training pairs extracted from two-layer ASR results, , we feed them to the learning scheme which could be Perceptron or SVM. In this study, we investigate the SVM machine learning algorithm which is more robust for outlier samples [27]. … Related articles All 2 versions

Speech Recognition in Indian Languages—A Survey M Sarma, KK Sarma – Recent Trends in Intelligent and Emerging Systems, 2015 – Springer … a few phonemes or a few words or isolated digits, with good success [25–27], using pattern mapping by multilayer perceptron (MLP). … where a spoken dialogue system is designed to use in agricultural commodities task domain using real-world speech data collected from two … Related articles All 5 versions

Deep neural network acoustic models for spoken assessment applications J Cheng, X Chen, A Metallinou – Speech Communication, 2015 – Elsevier … In addition to the educational systems discussed above, there is a variety of other CALL applications (eg Eskenazi, 2009) that make use of an ASR engine, for example spoken dialog systems, learning game … A DNN is a multi-layer perceptron (MLP) with many hidden layers. … Cited by 2 Related articles All 3 versions

Data-driven deep-syntactic dependency parsing M BALLESTEROS, B BOHNET… – Natural Language …, 2015 – Cambridge Univ Press Page 1. Natural Language Engineering: page 1 of 36. c Cambridge University Press 2015 doi:10.1017/S1351324915000285 1 Data-driven deep-syntactic dependency parsing† MIGUEL BALLESTEROS1, BERND BOHNET2 … Cited by 2 Related articles All 3 versions

Learner corpora and natural language processing D Meurers – The Cambridge handbook of learner corpus research. …, 2015 – purl.org Page 1. Learner Corpora and Natural Language Processing Detmar Meurers Universität Tübingen Revision 8474 Core issues, notions, and methods Learner corpora collect the language produced by people learning their first or a second lan- guage. … Cited by 5 Related articles All 3 versions

Listen, attend, and walk: Neural mapping of navigational instructions to action sequences H Mei, M Bansal, MR Walter – arXiv preprint arXiv:1506.04089, 2015 – arxiv.org … ?tj = exp(?tj)/ ? j exp(?tj), (6) where the alignment term ?tj = f(st?1,xj,hj) weighs the extent to which the word at position j and those around it match the output at time t. The alignment is modelled as a one-layer neural perceptron ?tj = v tanh(Wst?1 + Uxj + V hj), (7) … Cited by 5 Related articles All 8 versions

Succeeding metadata based annotation scheme and visual tips for the automatic assessment of video aesthetic quality in car commercials F Fernández-Martínez, AH García… – Expert Systems with …, 2015 – Elsevier In this paper, we present a computational model capable to predict the viewer perception of car advertisements videos by using a set of low-level video descript. Cited by 2 Related articles All 7 versions

Maximum-likelihood normalization of features increases the robustness of neural-based spoken human-computer interaction E Trentin – Pattern Recognition Letters, 2015 – Elsevier … These limitations are the reason why several scientists have been proposing hybrid systems that combine the long-term modeling capabilities of HMMs and the flexibility [10] of artificial neural networks (ANN) [3]. Albeit traditional ANNs (eg, multilayer perceptrons and radial … Related articles All 3 versions

Soft-Computational Techniques and Spectro-Temporal Features for Telephonic Speech Recognition: An Overview and Review of M Sharma, KK Sarma – Handbook of Research on Advanced …, 2015 – books.google.com … The evaluation results reported by the authors here indicate high recognition accuracy up to 95% which makes the proposed solution a feasible one with addition to the existing spoken dialogue systems such as voice banking applications, call routes, voice portals, etc. … Related articles All 3 versions

Learning a game commentary generator with grounded move expressions H Kameko, S Mori, Y Tsuruoka – 2015 IEEE Conference on …, 2015 – ieeexplore.ieee.org … The prediction model outputs a d-dimensional real-valued vector, each of whose elements indicates whether a particular word should appear in a comment or not, where d is the size of vocabulary. We use a three-layer perceptron with binary outputs for building the model. Fig. … Related articles All 9 versions

Automating live and batch subtitling of multimedia contents for several European languages A Álvarez, C Mendes, M Raffaelli, T Luís… – Multimedia Tools and …, 2015 – Springer … The LVCSR engine named Audimus [31] is based on a hybrid speech recognition structure combining the temporal modeling capabilities of Hidden Markov Models (HMMs), with the pattern discriminative classification capabilities of Multilayer Perceptrons (MLPs). … Cited by 4 Related articles

Situated Learning and Understanding of Natural Language Y Artzi – 2015 – digital.lib.washington.edu … of tasks, including robotic interpretation of navigational directions and learning to understand user utterances in dialog systems. … in dialog systems and from human demonstrations in a situated learning regime. When integrated … Related articles All 4 versions

A Survey on perceived speaker traits: Personality, likability, pathology, and the first challenge B Schuller, S Steidl, A Batliner, E Nöth… – Computer Speech & …, 2015 – Elsevier The INTERSPEECH 2012 Speaker Trait Challenge aimed at a unified test-bed for perceived speaker traits – the first challenge of this kind: personality in the f. Cited by 8 Related articles All 14 versions

State-clustering based multiple deep neural networks modeling approach for speech recognition P Zhou, H Jiang, LR Dai, Y Hu… – IEEE/ACM Transactions …, 2015 – ieeexplore.ieee.org … Since the 1990s, the so-called multi-layer perceptron (MLP), has been used as an alternative to the GMM to compute posterior probabilities of mono- phone HMM states based on a fixed number of speech frames within a long context window [2]. These probabilities may be … Cited by 6 Related articles All 3 versions

Application of Machine Learning Algorithms for the Query Performance Prediction M Milicevic, M Baranovic, K Zubrinic – Advances in Electrical and …, 2015 – researchgate.net … System indicators should provide information that the system is working on the user’s problem. … pruning [41]; • IBk – a version of the k-nearest neighbours algorithm, used in k-nearest neighbours classification [42]; • linear regression; • neural network – multilayer perceptron [43-44 … Related articles All 2 versions

A syntactic component for Vietnamese language processing P Le-Hong, A Roussanaly… – Journal of Language …, 2015 – hal.archives-ouvertes.fr Page 1. A syntactic component for Vietnamese language processing Phuong Le-Hong, Azim Roussanaly, Thi Minh Huen Nguyen To cite this version: Phuong Le-Hong, Azim Roussanaly, Thi Minh Huen Nguyen. A syntactic component for Viet- namese language processing. … Cited by 4 Related articles All 6 versions

Multitask learning of deep neural networks for low-resource speech recognition D Chen, BKW Mak – IEEE/ACM Transactions on Audio, Speech, …, 2015 – ieeexplore.ieee.org … For example, [37] applies MTL on a single convolutional neural network to produce state-of-the-art performance for several language processing predictions; [38] improves intent classification in goal-oriented human-machine spoken dialog systems which is particularly … Cited by 2 Related articles All 4 versions

Effective use of cross-domain parsing in automatic speech recognition and error detection MA Marin – 2015 – digital.lib.washington.edu … information, we attempt to detect their location and extent (within the ASR hypothesis), as well as the type, in order to handle them effectively during the subsequent clarification request made by the dialog system component. In particular we are interested in two types … Cited by 2 Related articles All 2 versions

Combining multiple parallel streams for improved speech processing JTR de Sousa Miranda – 2015 – l2f.inesc-id.pt … MFCC Mel-Frequency Cepstral Coefficients MLP Multilayer Perceptron MT Machine Translation … retrieval engine to locate the most relevant documents. • Spoken dialog systems [82, 54] may collaborate with a user in spoken language to com- plete a certain task. … Related articles All 2 versions

[BOOK] Language Identification Using Excitation Source Features KS Rao, D Nandi – 2015 – Springer … Some of the topics covered in this series include the presentation of real life commercial deployment of spoken dialog systems, contemporary methods of speech parameterization, developments in information security for automated speech, forensic speaker recognition, use … Related articles All 6 versions

Speech recognition based confidence measures for building voices from untranscribed speech TS Godambe – 2015 – web2py.iiit.ac.in … Carnegie Mellon University False Acceptance False Rejection Mel Cepstral Distortion Mel Frequency Cepstral Coefficients Multilayer Perceptron Mean Opinion Score Non-Standard Words Phone Error Rate Statistical Sarametric Synthesis True Acceptance True Rejection … Related articles

Incremental recurrent neural network dependency parser with search-based discriminative training M Yazdani, J Henderson – 2015 – archive-ouverte.unige.ch … It also easily supports incremental in- terpretation in dialogue systems, or incremental language modeling for speech recognition. … best actions, previous work has proposed memory-based clas- sifiers (Nivre et al., 2004), SVMs (Nivre et al., 2006), structured perceptron (Huang et … Cited by 5 Related articles All 9 versions

Automated Quality Assurance of Non-Functional Requirements for Testability A Rashwan – 2015 – spectrum.library.concordia.ca … NFR Non-Functional Requirement NLP Natural Language Processing NN Neural Network NR Non Requirement OWL Web Ontology Language PAUM Perceptron Algorithm with Uneven Margins POS Part-of-speech xii Page 13. PR Processing Resources QA Quality Assurance … Related articles All 3 versions

Structural information aware deep semi-supervised recurrent neural network for sentiment analysis W Rong, B Peng, Y Ouyang, C Li, Z Xiong – Frontiers of Computer Science, 2015 – Springer Page 1. Front. Comput. Sci., 2015, 9(2): 171–184 DOI 10.1007/s11704-014-4085-7 Structural information aware deep semi-supervised recurrent neural network for sentiment analysis Wenge RONG1,2, Baolin PENG1, Yuanxin OUYANG 1,2, Chao LI1,2, Zhang XIONG1,2 … Cited by 2 Related articles All 4 versions

Spoken content retrieval—beyond cascading speech recognition with text retrieval L Lee, J Glass, H Lee, C Chan – IEEE/ACM Transactions on …, 2015 – ieeexplore.ieee.org Page 1. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 23, NO. 9, SEPTEMBER 2015 1389 Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval … Cited by 4 Related articles All 6 versions

Novel Methods for Text Preprocessing and Classification T Gasanova – 2015 – deutsche-digitale-bibliothek.de … 87 2.17 Co-Operation of Biology Related Algorithms (COBRA) . . . . 89 3.1 Overview of Spoken Dialogue Systems . . . . . 105 4.1 Common diagramm of text preprocessing and text classification . . . . . … Related articles

Sentiment Analysis of M&S Customers Reviews A Alharbi – 2015 – vlebb.leeds.ac.uk … Different machine learning algorithms that are designed for forecasting time series data are examined for instance linear regression, multilayer perceptron and support vector regression. … 6.3.2. Multilayer perceptron …………… 51 … Related articles

Resource-Dependent Acoustic and Language Modeling for Spoken Keyword Search IF Chen – 2015 – smartech.gatech.edu … 72 5.3.1 Global linear models 73 5.3.2 The perceptron algorithm 74 5.3.3 Issues in the conventional DLM approaches 76 … Related articles

Natural Language Processing for Social Media A Farzindar, D Inkpen – Synthesis Lectures on Human …, 2015 – morganclaypool.com … Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 … Cited by 4 Related articles All 5 versions

Frame-Level Features Conveying Phonetic Information for Language and Speaker Recognition MD Sánchez – 2015 – Citeseer Page 1. University of The Basque Country Doctoral Thesis Frame-Level Features Conveying Phonetic Information for Language and Speaker Recognition Author: Mireia Diez Sánchez Supervisors: Dra. Amparo Varona Dr. German Bordel … Related articles All 4 versions

Semi-Autonomous Data Enrichment and Optimisation for Intelligent Speech Analysis Z Zhang – 2015 – mediatum.ub.tum.de … feature aspect. Generally, a Wizard-of-Oz (WOZ) is designed at the beginning (eg, a multi-model dialogue system), then elicits the speakers to a prede- termined state, giving rise to the provoking of utterances ‘naturally’. Normally … Related articles All 3 versions

Multi-task Learning Deep Neural Networks for Automatic Speech Recognition D Chen – 2015 – cse.ust.hk … 11 2.3 Relationship between the four ANNs in this section. 15 2.4 Multilayer perceptron. 16 … dictions; [20] improves intent classification in goal-oriented human-machine spoken dialog systems which is particularly successful when the amount of labeled training … Related articles

[BOOK] Biometric and intelligent decision making support A Kaklauskas – 2015 – Springer Page 1. Intelligent Systems Reference Library 81 Arturas Kaklauskas Biometric and Intelligent Decision Making Support Page 2. Intelligent Systems Reference Library Volume 81 Series editors Janusz Kacprzyk, Polish Academy … Cited by 5 Related articles All 4 versions

Paralinguistic event detection in children’s speech H Rao – 2015 – smartech.gatech.edu Page 1. PARALINGUISTIC EVENT DETECTION IN CHILDREN’S SPEECH A Thesis Presented to The Academic Faculty by Hrishikesh Rao In Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy in the School of Electrical and Computer Engineering … Related articles

Deep learning approaches to problems in speech recognition, computational chemistry, and natural language text processing GE Dahl – 2015 – tspace.library.utoronto.ca … Backpropagation promised to train nets with one or more layers of hidden units capable of learning their own features instead of relying entirely on hand-engineered features the way (zero hidden layer) perceptron networks did. … Cited by 1 Related articles All 5 versions

Sentiment analysis of real-life situations using location, people and time as contextual features HJ Do, HJ Choi – 2015 International Conference on Big Data …, 2015 – ieeexplore.ieee.org … suPPOtt vcctor machines,” Perception in Multilllodal Dialogue Systems, pp. 205-216, 2008. [5] T. Danislllan, IM Bilasco, J. Martinet, C. Djeraba, Itlntelligent pixels of interest selection with application to facial expression recognition using nlultilayer perceptron:’ Signal Processing … Related articles All 2 versions