FSG (Finite State Grammar) & Dialog Systems


 


[PDF] Speech and language processing [PDF] from colorado.edu D Jurafsky… – 2008 – cs.colorado.edu … A similar spoken dialogue system has been deployed by as- tronauts on the International Space Station. … 1956) first considered finite- state machines as a way to characterize a grammar and defined a finite-state language as a language generated by a finite-state grammar. … Cited by 305 – Related articles – View as HTML – All 21 versions

Dynamic Language Modeling Using Bayesian Networks for Spoken Dialog Systems [PDF] from oregonstate.edu A Raux, N Mehta, D Ramachandran… – … Annual Conference of …, 2010 – isca-speech.org … [6] present an alternative approach where the state-dependent language models are finite-state grammars rather than SLMs. … This is problematic because understanding the user intention is key to the success of a dialog system. Gruenstein et al. … Cited by 2 – Related articles – All 2 versions

A spoken dialog system based on automatically-generated example database A Ito, T Morimoto, S Makino… – Audio Language and …, 2010 – ieeexplore.ieee.org … D. Discussion The proposed framework generates example sentences from a simple description of the task. This framework is similar to several existing spoken dialog systems [6, 7], which generates finite state grammar from a task description. … Cited by 1 – Related articles

A speech understanding framework that uses multiple language models and multiple understanding models [PDF] from brandeis.edu M Katsumaru, M Nakano, K Komatani… – Proceedings of Human …, 2009 – dl.acm.org … The speech understanding component in a spoken dialogue system consists of an automatic speech recognition (ASR) component and a language un- derstanding … There are many types of LMs such as finite-state grammars and N-grams, and many types of LUMs such as finite … Cited by 3 – Related articles – All 15 versions

CARDIAC: An intelligent conversational assistant for chronic heart failure patient heath monitoring [PDF] from rochester.edu G Ferguson, J Allen, L Galescu, J Quinn… – AAAI Fall Symposium …, 2009 – aaai.org … CARDIAC is an agent-based spoken dialogue system that conducts health monitoring interviews with chronic heart failure patients using … of collecting domain-specific utter- ances, then generalizing them (via synonyms and rephras- ing) into a finite-state grammar from which we … Cited by 6 – Related articles – All 13 versions

Speech recognition in a dialog system for patient health monitoring [PDF] from rochester.edu L Galescu, J Allen, G Ferguson… – … , 2009. BIBMW 2009. …, 2009 – ieeexplore.ieee.org … II. OVERVIEW OF THE SYSTEM CARDIAC is an agent-based spoken dialogue system that conducts health monitoring interviews with chronic … of collecting domain-specific utterances, then generalizing them (via synonyms and rephrasing) into a finite-state grammar from which … Cited by 1 – Related articles – All 16 versions

Utterance Classification for Combination of Multiple Simple Dialog Systems SJ Hahm, A Ito, K Awano, M Ito… – Parallel and Distributed …, 2011 – ieeexplore.ieee.org … At first, the input utterance is recognized by speech recognizers using a large vocabulary N-gram grammar as well as finite state grammars (FSGs) automatically generated for frame-based dialog subsystems. … Figure 2. Overview of the proposed dialog system … Related articles – All 2 versions

Improving speech understanding accuracy with limited training data using multiple language models and multiple understanding models [PDF] from kyoto-u.ac.jp M Katsumaru, M Nakano, K Komatani… – … Annual Conference of …, 2009 – isca-speech.org … greatly depends on the quality of the LM and LUM [1], the se- lection of the LM and LUM and their combination is critical in delivering spoken dialogue systems in real-world applications. For statistical models, much training data is needed. For finite- state grammar-based models … Cited by 2 – Related articles – All 9 versions

[PDF] A Two-Stage Domain Selection Framework for Extensible Multi-Domain Spoken Dialogue Systems [PDF] from kyoto-u.ac.jp M Nakano, S Sato, K Komatani… – Proc. of the …, 2011 – winnie.kuis.kyoto-u.ac.jp … These methods can be applied to domain selection in multi-domain spoken dialogue systems. … expert class QA IP RU LM for ASR trigram trigram finite-state grammar language keyphrase keyphrase finite-state understanding -based -based transducer vocabulary 1,140 407 79 … Related articles – View as HTML – All 7 versions

An introduction to voice search YY Wang, D Yu, YC Ju… – … Processing Magazine, IEEE, 2008 – ieeexplore.ieee.org … SPOKEN DIALOG SYSTEMS ARE OFTEN CHRONOLOGICALLY CATEGORIZED INTO THREE GENERATIONS: INFORMATIONAL, TRANSACTIONAL, AND PROBLEM … LANGUAGE MODELING Early DA systems compiled directory entries into a finite-state grammar as the … Cited by 42 – Related articles – BL Direct – All 5 versions

Extracting Events and Temporal Expressions from Text [PDF] from rochester.edu N UzZaman… – Semantic Computing (ICSC), 2010 …, 2010 – ieeexplore.ieee.org … structure of documents and apply the temporal structure in other applications like textual entailment, question answering, dialog systems or others. … Boguraev and Ando’s work is based on a cascaded finite-state grammar (500 stages and 15000 transitions) and Kolomiyets and … Cited by 2 – Related articles – All 16 versions

Modelling illocutionary structure: combining empirical studies with formal model analysis H Shi, R Ross, T Tenbrink… – Computational Linguistics and …, 2010 – Springer … Through the use of appropriate tools such finite- state grammars can be formally analysed and validated against empir- ically collected corpora. … To achieve natural interaction with artificial systems, we believe it necessary for dialogue systems to leverage sufficiently off linguistic … Cited by 1 – Related articles – All 2 versions

LEXICAL ACQUISITION APPARATUS, MULTI DIALOGUE BEHAVIOR SYSTEM, AND LEXICAL ACQUISITION PROGRAM M Nakano, T Nose, R Taguchi… – US Patent App. 12/ …, 2010 – Google Patents … Systems, Vol. 56, No. 11, pp. 1004-1013 (2008) [0013] [Non-Patent Literature 5] O’Neill, IM and McTear, M. E: Object-oriented modelling of spoken language dialogue systems, Natural Language Engineering, Vol. 6, No. 3&4, pp. 341 … All 2 versions

[PDF] Automatic Fingersign to Speech Translator [PDF] from boun.edu.tr P Campr, E Dikici, M Hruz… – Proc. 6-th Summer …, 2010 – busim.ee.boun.edu.tr … In framework of the given project a multilingual ASR system is constructed applying the Hidden Markov Model Toolkit (HTK version 3.4) [8]. Language models based on statistical text analysis and finite-state grammars are implemented for ASR of continuous phrases or … Cited by 2 – Related articles – View as HTML

Robust spoken instruction understanding for HRI [PDF] from tufts.edu R Cantrell, M Scheutz… – … -Robot Interaction (HRI …, 2010 – ieeexplore.ieee.org … We have chosen the latter approach, using the CMUSphinx speech recognition system,1 in conjunction with a CMU acoustic model (WSJ) and a hand- crafted finite-state grammar to reduce word error rates. It should be noted … Cited by 10 – Related articles – All 3 versions

Grounding new words on the physical world in multi-domain human-robot dialogues [PDF] from nict.go.jp M Nakano, N Iwahashi, T Nagai, T Sumii… – 2010 AAAI Fall …, 2010 – aaai.org … So far many researchers have tackled multi-domain spo- ken dialogue systems. … One is a finite- state-grammar-based language model, which is the union of grammars supposed by the experts other than name acquisi- tion experts. … Cited by 1 – Related articles – All 3 versions

Managing multiple speech-enabled applications in a mobile handheld device M Schuricht, Z Davis, M Hu, S Prasad… – International …, 2009 – emeraldinsight.com … Finite state grammars are commonly used for traditional command and control applications, while statistical models are used in more advanced natural … Butler (2004) is a spoken dialog system for mobile environments that uses a single, individualized speech interface to provide … Cited by 1 – Related articles

Spoken Dialogue Systems K Jokinen… – Synthesis Lectures on Human …, 2009 – morganclaypool.com … acoustic modelling, whereas the language model uses either n-grams that estimate the likelihood of sequences of words or finite state grammars that model permissible word sequences. Given these two probabilities, the 6. 7. 8. 1. 2. Page 20. 6 SPoKEN DIALoGUE SySTEMS … Cited by 12 – Related articles – Library Search – All 5 versions

System and method for speech-to-text conversion using constrained dictation in a speak-and-spell mode A Rao – US Patent 7,676,364, 2010 – Google Patents … The Command-and-Control systems usually resort to finite state grammars. … For example, the MIT Laboratory of Computer Science has published a research paper (refer to “Automatic Acquisition of Names Using Speak and Spell Mode in Spoken Dialogue Systems”, Seneff and … Related articles – All 3 versions

History and Development of Speech Recognition S Furui – Speech Technology, 2010 – Springer … 2-way dialogue transcription network agent & intelligent messaging network agent & intelligent messaging system driven dialogue system driven dialogue … The most per- vasive is the finite-state grammar, which provides an integrated mechanism for addressing both variations in … Cited by 3 – Related articles – All 2 versions

Enhancing Accessibility through Speech Technologies on AAL Telemedicine Services for iTV H Delgado, A Rodriguez-Alsina, A Gurguí… – Ambient …, 2011 – Springer … In this situation, the language can be modeled through finite state grammars rather than statistical N-grams. … Unlike conventional dictation systems in medial environment, the implemented module may be considered as a spoken dialogue system intended to introduce medical …

[PDF] Event and temporal expression extraction from raw text: First step towards a temporally aware system [PDF] from rochester.edu N UZZAMAN, JF ALLEN – International Journal of Semantic …, 2011 – cs.rochester.edu … Boguraev and Ando’s work is based on a cascaded finite-state grammar (500 stages and 15000 transitions) and Kolomiyets and Moens first filter certain phrase types and grammatical categories as candidates for temporal expressions and then apply Maximum Entropy … Cited by 3 – Related articles – View as HTML – All 12 versions

Optimizing speech recognition grammars using a measure of similarity between hidden Markov models [PDF] from ku.edu.tr B Mohanty, J Hershey, P Olsen… – Acoustics, Speech and …, 2008 – ieeexplore.ieee.org … 1. INTRODUCTION In spoken dialog systems, stochastic finite state grammars (FSG) are often used for speech recognition at dialog states. In order to han- dle words and phrases outside the grammar, these grammars typi- cally … Cited by 2 – Related articles – All 5 versions

Shareable filler model for grammar authoring A Acero, D Yu, YY Wang… – US Patent 7,865,357, 2011 – Google Patents … 30-Dec.4, 1998.* Wang, Kuansan. Semantic Modeling for Dialog Systems in a Pattern Recognition Framework. Proc. … 1870-1878. Qiquang Lin et al., “Key-Phrase Spotting using an Integrated Lan- guage Model of N-Grams and Finite-State Grammar,” In Proc. … Related articles – All 4 versions

System and method for providing network coordinated conversational services SH Maes… – US Patent 7,519,536, 2009 – Google Patents Page 1. Illllllllllllllllllllllllllllllllllllllllllllllli US007519536B2 (12) United States Patent ao) Patent no.: us 7,519,536 B2 Maesetal. (45) Date of Patent: * Apr. 14, 2009 (54) SYSTEM AND METHOD FOR PROVIDING NETWORK COORDINATED … Cited by 9 – Related articles – All 4 versions

[PDF] Automatically assessing the oral proficiency of proficient L2 speakers [PDF] from bham.ac.uk PFDV Müller, F De Wet, C Van der Walt… – Proceedings of …, 2009 – eee.bham.ac.uk … 2.2. Test implementation A spoken dialogue system (SDS) guided students through the test and captured their answers. … For each sentence in the the reading task, a finite-state grammar was constructed allowing two options: the target ut- terance and “I don’t know”. … Cited by 5 – Related articles – View as HTML – All 4 versions

New perspectives on spoken language understanding: Does machine need to fully understand speech? [PDF] from kyoto-u.ac.jp T Kawahara – … & Understanding, 2009. ASRU 2009. IEEE …, 2009 – ieeexplore.ieee.org … In this article, new perspectives on SLU based on these observations are reviewed. In Section II, SLU for the new- generation spoken dialogue systems is discussed. … ASRU 2009 46 Page 2. Finite State Grammar mapping to SQL (slot filling) state-action pair … Cited by 5 – Related articles – All 6 versions

Automatic Understanding of ATC Speech: Study of Prospectives and Field Experiments for Several Controller Positions [PDF] from upm.es JM Pardo, J Ferreiros, F Fernandez… – Aerospace and …, 2011 – ieeexplore.ieee.org Page 1. Automatic Understanding of ATC Speech: Study of Prospectives and Field Experiments for Several Controller Positions JM PARDO, Senior Member, IEEE J. FERREIROS, Senior Member, IEEE F. FERN ´ANDEZ, V. SAMA … Cited by 2 – Related articles – All 3 versions

SmartWeb handheld-multimodal interaction with ontological knowledge bases and semantic web services [PDF] from dfki.de D Sonntag, R Engel, G Herzog, A Pfalzgraf… – Artifical Intelligence for …, 2007 – Springer … Text Generation Within the dialog system, the text generation module is used within two pro- cessing steps. … As these dialog moves can be regarded as adjacency pairs, the dialog behaves according to some finite state grammar for QA, which makes up the automa- ton part (FSA … Cited by 46 – Related articles – BL Direct – All 21 versions

Dialog strategies for handling miscommunication in task-related HRI [PDF] from tum.de B Gonsior, C Landsiedel, A Glaser… – RO-MAN, 2011 …, 2011 – ieeexplore.ieee.org … finite-state grammars for speech recognition were created for each input node. During the experiment, a route displayed on a map was presented to the subjects for each of the dialog strategies separately. Then, subjects were asked to interact with the dialog system, which … Related articles – All 2 versions

System and method for providing network coordinated conversational services SH Maes… – US Patent App. 12/386,166, 2009 – Google Patents Page 1. US 20090287477A1 (i9) United States (12) Patent Application Publication oo) Pub. No.: US 2009/0287477 Al Maes et al. (43) Pub. Date: Nov. 19,2009 (54) SYSTEM AND METHOD FOR PROVIDING NETWORK COORDINATED … All 2 versions

Effective acoustic adaptation for a distant-talking interactive TV system [PDF] from fbk.eu J Huang, M Epstein… – Ninth Annual Conference of …, 2008 – isca-speech.org … using a grammar to compute class probability “#%’)01345779 , where words are generated by the probabilistic finite-state grammar correspond- ing to the class. After ASR has generated sentences of decoded words and embedded grammars, the dialog system then uses a … Cited by 7 – Related articles – All 4 versions

Improved language modeling for conversational applications using sentence quality [PDF] from mirlab.org M Epstein, B Ramabhadran… – Acoustics Speech and …, 2010 – ieeexplore.ieee.org … sentence quality: sentence length, direct- ness, grammaticality, awkwardness, frequency of N-grams, and the appropriateness of the response to the state of the dialog system. … The words within each embed- ded grammar are implemented by probabilistic finite state grammars. … Related articles – All 4 versions

[PDF] Automatic speech recognition for assistive technology devices [PDF] from icdvrat.org AP Harvey, RJ McCrindle, K Lundqvist… – 2010 – icdvrat.org … part of the ENABLE ASR system: ? Development of a new language (audio) model based on a Finite State Grammar which forms … transcription.com/ Patras (2010), Wire Communications Laboratory, http://www.wcl.ece.upatras.gr/ Patras (2010), A Dialogue System for Telephone … View as HTML

Voice search for development [PDF] from csir.co.za E Barnard, J Schalkwyk, C Heerden… – … Annual Conference of …, 2010 – isca-speech.org … Such developments would require a new class of user interfaces, which would be somewhat similar to current spoken dialog systems. … (We also used a manually crafted finite-state grammar to gener- ate an additional set of domain-specific Zulu prompts.) Data collection utilized … Cited by 3 – Related articles – All 11 versions

Automatic assessment of oral language proficiency and listening comprehension F De Wet, C Van der Walt… – Speech Communication, 2009 – Elsevier … The automatic test is implemented as a spoken dialogue system and consists of a reading as well as a repeating task. … 2.2. Test implementation. A spoken dialogue system (SDS) was developed to guide students through the test and to capture their answers. … Cited by 7 – Related articles – All 3 versions

Emotion Detection Device and Method for Use in Distributed Systems IM Bennett – US Patent App. 20,100/036,660, 2009 – freepatentsonline.com … The SRI Open Agent Architecture (OAA) is a framework for integrating the various components that comprise a spoken dialogue system. … Optionally, if dialogs are written as finite state grammars, the UNIANCE compiler [Bos, J., Compilation of Unification Grammars with … Cached

Emotion Detection Device and Method for Use in Distributed Systems IM Bennett – US Patent App. 12/579,233, 2009 – Google Patents Page 1. (i9) United States (12) Patent Application Publication Bennett US 20100036660A1 (io) Pub. No.: US 2010/0036660 Al (43) Pub. Date: Feb. 11, 2010 (54) EMOTION DETECTION DEVICE AND METHOD FOR USE IN …

Exploiting Predictable Response Training to Improve Automatic Recognition of Children’s Spoken Responses [PDF] from cmu.edu W Chen, J Mostow… – Intelligent Tutoring Systems, 2010 – Springer … Our language model generator then compiles the resulting questions into a finite state grammar (FSG). Fig. … In: HLT-NAACL, Association for Computational Linguistics, Boston, pp. 25-28 (2004) 2. Litman, DJ, Silliman, S.: ITSPOKE: an intelligent tutoring spoken dialogue system. … All 4 versions

[PDF] Language resources and CALL applications: speech data and speech technology in the DISCO project [PDF] from ru.nl H Strik, J Colpaert, J van Doremalen… – … and Semantic Data, 2010 – lands.let.ru.nl … some typical phenomena of human-machine interaction that are known to be problematic in the development of spoken dialogue systems, such as … This list is the basis for a Finite State Grammar (FSG) language model, which is used by an hidden Markov model (HMM)-based … Related articles – View as HTML – All 13 versions

Voice Search YY Wang, D Yu, YC Ju… – Spoken Language …, 2009 – Wiley Online Library … Dialogue system tuning is often performed painstakingly by spoken dialogue experts, starting from error analysis on the logged interaction data to find the flaws in the … Early DA systems compiled directory entries into a finite-state grammar as the language model for ASR. … Related articles – All 4 versions

[PDF] Lexicons and Grammars for Named Entity Annotation in the National Corpus of Polish [PDF] from nkjp.pl A Savary… – Intelligent Information Systems, Siedlce, Poland, 2010 – nkjp.pl … lingual NLP platform. It is equipped with a set of reusable Unicode-capable on-line processing components for basic linguistic operations and a cascaded unification- based finite-state grammar parser and interpreter. The basic … Cited by 4 – Related articles – View as HTML – All 4 versions

Automatic fingersign-to-speech translation system M Hrúz, P Campr, E Dikici, AA Kindiroglu… – Journal on Multimodal …, 2011 – Springer … Language models based on statistical text analysis and finite-state grammars are implemented for ASR of continuous phrases or mes- sages [45]. 2.4 Speech synthesis Speech synthesis is the artificial production of human speech. … Related articles – All 2 versions

Evaluation of a Voice-Based Internet Browser with Untrained and Trained Users KP Engelbrecht, C Wootton, I Wechsung… – Universal Access in …, 2009 – Springer … to the available content from the RSS feeds, by using the widely accepted COSIM function, which is seen in other dialog systems such as … The dynamic development and maintenance of the system-directed finite state grammar is relatively simple, as at any stage in the dialog the … Related articles – All 4 versions

Language pattern analysis for automotive natural language speech applications [PDF] from auto-ui.org U Winter, TJ Grost… – … of the 2nd International Conference on …, 2010 – dl.acm.org … into a raw textual utterance. This engine is either based on Statistical Language Models with slots for data or on sophisticated Finite State Grammars, modeling a variety of typical natural utterances. A semantic interpreter (often … Related articles – All 2 versions

Natural language system and method based on unisolated performance metric S Deligne, Y Gao, V Goel, HK Kuo… – US Patent 7,574,358, 2009 – Google Patents … 1998. B. Souvignier et al, “Online adaptation for language models in spo- ken dialogue systems,” in Proc. … V. Goel, “Conditional maximum likelihood estimation for improving annotation performance of N-gram models incorporating stochastic finite state grammars,” in Proc. … Cited by 1 – Related articles – All 3 versions

A prototype of distant-talking interface for control of interactive TV M Omologo – … (ASILOMAR), 2010 Conference Record of the …, 2010 – ieeexplore.ieee.org … under DICIT, based on IBM Embedded ViaVoice (EVV) [4], is speaker independent and supports the use of large vocabular- ies, finite state grammars with structured … 5] R. Balchandran, M. Epstein, G. Potamianos, and L. Seredi, A multi-modal spoken dialog system for interactive … Related articles

[PDF] Voice search an introduction [PDF] from microsoft.com Y Wang, D Yu, Y Ju… – IEEE Signal Processing …, 2008 – research.microsoft.com … Feedback loop: No systems can be perfectly built at the initial deployment. Dialog system tuning is often … 59.8%. Language Modeling: Early DA systems compiled directory entries into a finite-state grammar as the language model for ASR. … Cited by 1 – Related articles – View as HTML

[PDF] Unifying Speech Resources for Tone Languages: A Computational Perspective [PDF] from ijcis.info ME Ekpenyong, EAE Urua, VJ Ekong… – International Journal of …, 2011 – ijcis.info … (ii) Training and test data: for speech recognition and synthesis researchers (iii) Corpora and corpora processing tools: for researchers working on dialog systems (iv) Corpora from spoken … Well formed sequences are predicted by the finite state grammar (FSG) [13] in Figure 6. … Related articles – View as HTML – All 2 versions

ASR post-correction for spoken dialogue systems based on semantic, syntactic, lexical and contextual information [PDF] from cnrs.fr R López-Cózar… – Speech Communication, 2008 – Elsevier … If the dialogue system does not use word-classes but uses finite-state grammars, which is the case for many commercial systems based on VoiceXML, it is possible to save time in creating the word-classes by re-using the vocabulary in the grammars, which is usually arranged … Cited by 6 – Related articles – All 10 versions

Usability assessment of text-to-speech synthesis for additional detail in an automated telephone banking system H Morton, N Gunson, D Marshall, F McInnes… – Computer Speech & …, 2011 – Elsevier … The four studies described in this paper detail the evaluation of the usability of TTS within an already established dialogue system. … Natural language understanding (NLU) is implemented in the system via a finite-state grammar, in which allowable sequences of words and … Related articles – All 3 versions

An iterative relative entropy minimization-based data selection approach for n-gram model adaptation [PDF] from usc.edu A Sethy, PG Georgiou… – Audio, Speech, and …, 2009 – ieeexplore.ieee.org … We present results on language model adaptation using two speech recogni- tion tasks: a medium vocabulary medical domain doctor-patient dialog system and a large vocabulary transcription system for European Parliamentary Plenary Speeches (EPPS). … Cited by 6 – Related articles – All 5 versions

SYSTEM AND METHOD FOR PROVIDING NETWORK COORDINATED CONVERSATIONAL SERVICES SH Maes… – EP Patent 1,125,279, 2008 – freepatentsonline.com … is particularly useful to meet the growing demand in the embedded and pervasive computing world as well as NLU/NLG dialog systems. … can be designed in accordance with the present invention so that if the user’s request requires FSG (finite state grammar), the request can be … Related articles – Cached

Methods and Systems for Query-Based Searching Using Spoken Input IM Bennett – US Patent App. 20,100/228,540, 2010 – freepatentsonline.com … Lewis, D. (1979). Scorekeeping in a language game. Journal of Philosophical Logic 6,339-359. Litman, DJ, Pan, Shimei, Designing and evaluating an adaptive spoken dialogue system, User Modeling and User Adapted Interaction, 12,2002. Lochbaum, K. (1994). … Cached

Methods and Systems for Searching Using Spoken Input and User Context Information IM Bennett – US Patent App. 20,100/235,341, 2010 – freepatentsonline.com … Lewis, D. (1979). Scorekeeping in a language game. Journal of Philosophical Logic 6,339-359. Litman, DJ, Pan, Shimei, Designing and evaluating an adaptive spoken dialogue system, User Modeling and User Adapted Interaction, 12, 2002. Lochbaum, K. (1994). … Cached

[PDF] An overview on NLP in spoken HCI [PDF] from vu.nl X Wilcke – Amsterdam: Vrije Universiteit, 2010 – few.vu.nl … The main resources used in the literary search are the articles “Error handling in spoken dialogue systems: toward corrective … search task [2]. The decision for this approach, however, needed additional hand-crafted finite-state grammar to compensate for the lack of diversity in … Cited by 1 – Related articles – View as HTML – All 3 versions

Acquiring and Maintaining Knowledge by Natural Multimodal Dialog H Holzapfel – 2009 – deposit.ddb.de … Abstract While there have been various improvements and signification advancements in spoken dialog systems in recent years, today, dialog systems still have restricted adaptation abilities as dialog systems are generally being built as static systems with predefined and static … Related articles

Structure skeletons for efficient voice navigation through generic hierarchical objects SH Maes – US Patent 7,418,382, 2008 – Google Patents … Conventional instantiations of natural dialog systems, however, are designed such that the user follows a relatively narrow logic in the sequence or the elements that constitute 35 his or her query. This is true with FSG (Finite State Grammar) or pure statistical NLU systems. … Cited by 2 – Related articles – All 2 versions

[PDF] Improving Speech Recognition on a Mobile Robot Platform through the use of Top-Down Visual Queues [PDF] from ijcai.org J Robert, RPS Ross… – 2008 – ijcai.org … per- formance. Another approach uses dialog systems based on finite state grammar models or frame systems to antic- ipate user utterances from dialog constructs [Matsui, 1999; Bischoff, 2001]. Although these approaches … Related articles – View as HTML – All 6 versions

[PDF] Flexible turn-taking for spoken dialogue systems [PDF] from cmu.edu A Raux – 2008 – cs.cmu.edu Page 1. Flexible Turn-Taking for Spoken Dialogue Systems Antoine Raux January 2006 … Related Work 3.1 Turn-Taking Issues with Current Dialogue Systems The vast majority of spoken dialogue systems use a pipeline architecture similar to the one represented in Figure 3.1. … Cited by 2 – Related articles – View as HTML

Robust acoustic and semantic modeling in a telephone-based spoken dialog system [PDF] from uni-halle.de KT Mengistu – 2009 – deposit.ddb.de Robust Acoustic and Semantic Modeling in a Telephone-based Spoken Dialog System Kinfe Tadesse Mengistu (M. Sc.) … alog system. We also show the feasibility of building a robust, multi-domain telephone-based spoken dialog system framework that can be seamlessly used … Related articles – Library Search – All 4 versions

Building of Database for English-Azerbaijani Machine Translation Expert System [PDF] from cscjournals.org GZ Yusif – International Journal of Computational Linguistics ( …, 2011 – cscjournals.org … of the information systems dealing with processing of texts in natural languages, in particular, in dialogue systems, providing dialogue … or absence of changes on conditions and addition of missing elements formally represent computer realization of finite-state grammar or CFG … Related articles – All 4 versions

[PDF] Experiments in automatic assessment of oral proficiency and listening comprehension for bilingual South African speakers of English [PDF] from prasa.org F De Wet, PFDV Müller, C Van der Walt… – Proceedings of the …, 2008 – prasa.org … Test implementation A spoken dialogue system (SDS) was developed to guide stu- dents through the test and to capture their answers. … For each sentence in the the reading task, a finite-state grammar was constructed allowing two options: the target ut- terance and “I don’t know … Cited by 2 – Related articles – View as HTML – All 2 versions

[PDF] Practical Issues of Building Robust HMM Models Using HTK and SPHINX Systems [PDF] from 148.204.64.201 J Kacur… – … and Applications. F. Mihelic and J. Zibert. I- …, 2008 – 148.204.64.201 … been a great effort spent to build and employ ASR systems in areas like information retrieval systems, dialog systems, etc., but … dictionary related tasks, initializations and training methods, model enhancement and adaptation tools, it can use both finite state grammar (BNF) or … Cited by 3 – Related articles – View as HTML – All 4 versions

[PDF] Deliverable 4.1 Baseline components of speech activity detection, acoustic/speech event classification and distant-talking ASR for the DICIT scenario [PDF] from fbk.eu P Svaizer, M Matassoni, CZ FBK, J Huang… – 2009 – dicitweb.fbk.eu Page 1. Deliverable 4.1 Baseline components of speech activity detection, acoustic/speech event classification and distant-talking ASR for the DICIT scenario Authors: Piergiorgio Svaizer, Marco Matassoni, Christian Zieger (FBK); Jing Huang, Mark E. Epstein, Gerasimos … Related articles – View as HTML – All 4 versions

Garbage modeling with decoys for a sequential recognition scenario M Levit, S Chang… – … Speech Recognition & …, 2009 – ieeexplore.ieee.org … Research and Commercial Spoken Dialog Systems,” in Proceedings of 6th SIGdial Workshop on Discourse and Dialog, Lisbon, Portugal, September 2005 … PS Rao, “Key-phrase spot- ting using an integrated language model of n-grams and finite-state grammar,” in Proceedings … Cited by 2 – Related articles

Thai speech processing technology: A review C Wutiwiwatchai… – speech communication, 2007 – Elsevier … Acoustic modeling 5.3. Language modeling 5.4. Noise robustness 5.5. Prosody in ASR 6. Thai speech applications 6.1. Spoken dialogue systems 6.2. Speech translation 6.3. Speaker recognition 7. Language resources 7.1. Text resources 7.2. Speech resources 7.3. … Cited by 19 – Related articles – All 6 versions

[PDF] A Speech Interface to Virtual Environments [PDF] from psu.edu S McGlashan… – Swedish Institute of Computer Science, 2007 – Citeseer … We use a commercial recognition system (Nuance) which employs finite-state grammars for recognition. … In interactive dialogue systems, the role of the system is clear: it is a simulation of human agent for the information service, and the user can expect similar, albeit more limited … Cited by 1 – Related articles – View as HTML – All 12 versions

CONTROL AND CONFIGURATION OF A SPEECH RECOGNIZER BY WORDSPOTTING JA Arrowood – US Patent App. 20,090/037,176, 2008 – freepatentsonline.com … 20090076798, Apparatus and method for post-processing dialogue error in speech dialogue system using multilevel verification, March, 2009, Oh et al. … of a parcel tracking number that has a particular syntax that may be encoded in a grammar (such as a finite state grammar). … Cached

Modern standard Arabic based multilingual approach for dialectal Arabic speech recognition [PDF] from guc.edu.eg M Elmahdy, R Gruhn, W Minker… – … , 2009. SNLP’09. …, 2009 – ieeexplore.ieee.org … of Egyptian movies in the Arab world [4]. We have chosen the domain of connected digits speech recognition for this experiment for many reasons: • Most frequently used in spoken dialogue systems as it … The language model is a finite state grammar implemented with JSGF [15 … Cited by 2 – Related articles – All 2 versions

Connected Text Data System NS Ross – US Patent App. 20,090/157,387, 2008 – freepatentsonline.com … March, 2010 – 20100057460 SYSTEM AND METHOD FOR IMPROVING SYNTHESIZED SPEECH INTERACTIONS OF A SPOKEN DIALOG SYSTEM Syrdal et al … 20070276664, Method and system to generate finite state grammars using sample phrases, November, 2007, Khosla … Cached

Advanced front-end for robust speech recognition in extremely adverse environments [PDF] from ntua.gr D Dimitriadis, JC Segura, L Garcia… – … Annual Conference of …, 2007 – isca-speech.org … For example, in aeronautics, the lack of robustness prevents the more wide-spread introduction of spoken dialogue systems in fixed installations, such as the aircraft cockpit. … A finite-state grammar with perplexity equal to 14,9 is used as the language model. … Cited by 6 – Related articles – All 10 versions

The adaptive presentation assistant using grammar-based recognition to support the process of presenting [PDF] from utwente.nl L Satink – 2009 – essay.utwente.nl … spotting ….. 21 4.2.3 Grammar based recognition ….. 22 4.2.4 Finite state grammars ….. 23 4.2 … Related articles – All 2 versions

The multimodal presentation dashboard [PDF] from upenn.edu M Johnston, P Ehlen, D Gibbon… – … of the Workshop on Bridging the …, 2007 – dl.acm.org … doesn’t match the phrase on the slide, our for- giving stochastic model might return a speech re- sult like, “put up third quarter report mine.” The speech result is then mapped to the finite-state grammar, which catches … MATCH: An Ar- chitecture for Multimodal Dialogue Systems. … Cited by 1 – Related articles – All 19 versions

[PDF] Deliverable 7.1 Project Presentation, Dissemination and Use Plan [PDF] from fbk.eu M Omologo – 2008 – dicitweb.fbk.eu … For all the components necessary in the development of the targeted distant-talking dialogue system, research issues were addressed with the aim to produce both innovative results and robust solutions, in general characterized by a limited computational complexity. … Related articles – View as HTML – All 3 versions

[PDF] Speech-based Dictionary Application [PDF] from uta.fi T Lerlerdthaiyanupap – 2008 – cs.uta.fi … 3.3.2. Dialogue control …..23 4. Principles of spoken dialogue system development…..24 4.1. … In chapter 4, the principles including design guidelines of spoken dialogue system development are presented. … Related articles – View as HTML – All 3 versions

Natural Language System and Method Based on Unisolated Performance Metric S Deligne, Y Gao, V Goel… – US Patent App. 20,090/ …, 2008 – freepatentsonline.com … Automatic speech recognition (ASR) systems used in spoken dialogue systems are mostly based on statistical models; in particular, the maximum a posterior rule is used to find the best word sequence W for a given acoustic speech signal A. … Cached

Automatic oral proficiency assessment of second language speakers of South African English [PDF] from sun.ac.za PFV Muller – 2010 – ir1.sun.ac.za … 31 4.2.1 Finite State Grammar . . . . . 31 4.2.2 Unigram Language Model . . . . . 32 4.2.3 Oracle Finite State Grammar . . . . . 32 4.2.4 Oracle Alignment . . . . . … Related articles – All 4 versions

Natural Language System and Method Based on Unisolated Performance Metric S Deligne, Y Gao, V Goel, HK Kuo… – US Patent App. 12/ …, 2008 – Google Patents Page 1. (i9) United States (12) Patent Application Publication Deligne et al. US 20090030692A1 (io) Pub. No.: US 2009/0030692 Al (43) Pub. Date: Jan. 29, 2009 (54) NATURAL LANGUAGE SYSTEM AND METHOD BASED …

Meeting decision detection: multimodal information fusion for multi-party dialogue understanding [PDF] from ed.ac.uk PY Hsueh – 2009 – era.lib.ed.ac.uk Page 1. Meeting Decision Detection: Multimodal Information Fusion for Multi-Party Dialogue Understanding Pei-Yun Sabrina Hsueh T H E U NIVER S I T Y O F E DI NBU R G H Doctor of Philosophy Institute for Communicating and Collaborative Systems School of Informatics … Cited by 1 – Related articles – All 3 versions

Highly accurate children’s speech recognition for interactive reading tutors using subword units A Hagen, B Pellom… – Speech Communication, 2007 – Elsevier … In (Shobaki et al., 2000), a more extensive corpus consisting of 1100 children in grades K through 10 was collected in Oregon for US English and used to develop a speech recognition system for isolated word and finite-state grammar vocabularies. … Cited by 29 – Related articles – All 7 versions

Semantic Decoding of User Queries IM Bennett – US Patent App. 20,090/157,401, 2008 – freepatentsonline.com … Lewis, D. (1979). Scorekeeping in a language game. Journal of Philosophical Logic 6, 339-359. Litman, DJ, Pan, Shimei, Designing and evaluating an adaptive spoken dialogue system, User Modeling and User Adapted Interaction, 12, 2002. Lochbaum, K. (1994). … Cached

[PDF] DETECTING OFF-TASK SPEECH [PDF] from cmu.edu W Chen – 2012 – cs.cmu.edu … Page 18. 18 1.3.1.3 Out-of-domain utterance detection Out-of-domain (OOD) utterance detection sits in the context of dialog systems. It deals with the … using a finite state grammar automatically generated from the story sentence which penalizes repeating and skipping of words. … View as HTML

Hidden menu options in automated human-computer telephone dialogues: dissonance in the user’s mental model J Wilke, F McInnes, MA Jack… – Behaviour & Information …, 2007 – Taylor & Francis … Say it like you mean it: priming for structure in caller responses to a spoken dialogue system. … of all permissible speech inputs (along with corresponding touch-button options) for each input stage in the dialogue, resulting in handcrafted finite-state grammars against which caller … Cited by 1 – Related articles – BL Direct – All 6 versions

VOICE RECOGNITION CORRELATION RULE LEARNING SYSTEM, VOICE RECOGNITION CORRELATION RULE LEARNING PROGRAM, AND VOICE … K Abe – US Patent App. 20,100/100,379, 2009 – freepatentsonline.com … 20070136067, Audio dialogue system and voice browsing method, June, 2007, Scholl. … The recognized vocabulary recording unit 23 may furthermore record, for example, grammar data such a CFG (Context Free Grammar) or FSG (Finite State Grammar), or a word concatenation … Cached

Fuzzy GMM-based Confidence Measure Towards Keywords Spotting Application [PDF] from uwaterloo.ca MK Abida – 2007 – uwspace.uwaterloo.ca … error rate. 12 Page 21. The work in [3] presents a novel keyword spotting method: a combination of a Finite State Grammar (FSG) and a filler model, the two conventional technologies of keyword spotting. This mixed grammar … Cited by 2 – Related articles – All 8 versions

DYNAMIC NATURAL LANGUAGE UNDERSTANDING O Lavi, G Auerbach… – US Patent App. 20,080/ …, 2008 – freepatentsonline.com … In the system, a word lattice is generated for a string of ideographic characters using finite state grammars ( 150 ) and a system lexicon ( 240 … rug.nl/˜vannoord/papers/yearbook/node2.html as a part of a work called “Grammatical Analysis in a Spoken Dialogue System” by Gosse … Cached

SPEECH RECOGNITION BASED ON SYMBOLIC REPRESENTATION OF A TARGET SENTENCE N Duncan – US Patent App. 20,090/119,107, 2007 – freepatentsonline.com … speech coding of frames Heikkinen – October, 2005 – 20050228648 MULTI-STATE BARGE-IN MODELS FOR SPOKEN DIALOG SYSTEMS Ljolje – April, 2009 … 20070276664, Method and system to generate finite state grammars using sample phrases, November, 2007, Khosla. … Cached

DYNAMIC NATURAL LANGUAGE UNDERSTANDING O Lavi, G Auerbach… – US Patent App. 12/047,003, 2008 – Google Patents … No. 6,311,152 to Bai, et. al teaches a sys- tem (100, 200) for tokenization and named entity recognition of ideographic language. In the system, a word lattice is generated for a string of ideographic characters using finite state grammars (150) and a system lexicon (240). …

Constrained minimization and discriminative training for natural language call routing I Zitouni – Audio, Speech, and Language Processing, IEEE …, 2008 – ieeexplore.ieee.org … In designing a voice response system to handle these calls, it is not sufficient to in- clude in the automatic speech recognizer (ASR) just the names of the departments in the vocabulary or to use a hand-designed finite-state grammar, because what the caller may say cannot be … Cited by 1 – Related articles – BL Direct – All 4 versions

Natural Language Speech Lattice Containing Semantic Variants IM Bennett – US Patent App. 20,080/059,153, 2007 – freepatentsonline.com … 20080133240, Spoken dialog system, terminal device, speech information management device and recording medium with program recorded thereon, June, 2008, Miyata et al. 20090030680, Method and System of Indexing Speech Data, January, 2009, Mamou. … Cached

Statistical Language Model Trained With Semantic Variants IM Bennett – US Patent App. 20,080/052,078, 2007 – freepatentsonline.com … Lewis, D. (1979). Scorekeeping in a language game. Journal of Philosophical Logic 6, 339-359. Litman, DJ, Pan, Shimei, Designing and evaluating an adaptive spoken dialogue system, User Modeling and User Adapted Interaction, 12, 2002. Lochbaum, K. (1994). … Cached

Dynamic natural language understanding O Lavi, G Auerbach, E Persky – US Patent 7,216,073, 2007 – Google Patents … 706/45 2001/0009009 Al 7/2001 Iizuka FOREIGN PATENT DOCUMENTS WO WO 98/09288 3/1998 WO WO 99/14743 3/1999 WO WO 00/75863 A2 12/2000 OTHER PUBLICATIONS Noord et al., “Robust Grammatical Analysis for Spoken Dialogue Systems”, Natural Language … Cited by 7 – Related articles – All 5 versions

[BOOK] Speech processing for IP networks: Media resource control protocol (MRCP) D Burke – 2007 – books.google.com Page 1. Speech Processing for IP Networks Media Resource Control Protocol (MRCP) Dave Burke Page 2. Page 3. Speech Processing for IP Networks Page 4. Page 5. Speech Processing for IP Networks Media Resource Control Protocol (MRCP) Dave Burke Page 6. … Cited by 7 – Related articles – Library Search – All 6 versions

A detection-based pattern recognition framework and its applications [PDF] from gatech.edu C Ma – 2010 – smartech.gatech.edu Page 1. A DETECTION-BASED PATTERN RECOGNITION FRAMEWORK AND ITS APPLICATIONS A Thesis Presented to The Academic Faculty by Chengyuan Ma In Partial Fulfillment of the Requirements for the Degree Doctor … Cited by 1 – Related articles – Library Search – All 4 versions

A Computational Model for the Influence of Cross-Modal Context upon Syntactic Parsing P McCrae – 2010 – deposit.ddb.de Page 1. Universität Hamburg MIN-Fakultät Department Informatik A Computational Model for the Influence of Cross-Modal Context upon Syntactic Parsing Doctoral Thesis submitted by Patrick McCrae of Dublin Hamburg, March 2010 Page 2. … Cited by 1 – Related articles – Library Search – All 2 versions

[PDF] A Machine Learning Approach to Anaphora Resolution Including Named Entity Recognition, PP Attachment Disambiguation, and Animacy Detection [PDF] from psu.edu A Nøklestad – 2009 – Citeseer Page 1. A Machine Learning Approach to Anaphora Resolution Including Named Entity Recognition, PP Attachment Disambiguation, and Animacy Detection Anders Nøklestad May 7, 2009 Page 2. 2 For my parents, Randi and Hans Olaf Page 3. Contents 1 Introduction 13 … Cited by 1 – Related articles – View as HTML – All 4 versions