Language Modeling & Dialog Systems 2011

Language Model 

See also:

IRSTLM (IRST Language Modeling) Toolkit | Language Modelling | Maxent (Maximum Entropy Modeling Toolkit) 2011OpenOME (Organization Modelling Environment)Rule-based Language Modeling | SRILM (SRI Language Modeling Toolkit) 2011 | Tool for Agent Oriented Modeling for Eclipse (TAOM4E)


Semantic and dialogue processing in the VERBMOBIL spoken dialogue translation system [PDF] from uni-saarland.de E Maier… – 2011 – scidok.sulb.uni-saarland.de … MKK + 92] M. Mast, R. Kompe, F. Kummert, H. Niemann, and E. N oth. The dialog module of the speech recognition and dialog system EVAR. … Niedermair. Experiments in dialogue context dependent language modeling. In G unther G orz, editor, Pro- ceedings of KONVENS-92. … Cited by 11 – Related articles – All 14 versions

[BOOK] Spoken Language Understanding: Systems for Extracting Semantic Information from Speech G Tur, R De Mori – 2011 – books.google.com … respectively. He joined Microsoft in 1994. His research interests include spoken dialogue systems, natural language processing, language modeling, and voice search. Prior to joining Microsoft, he worked at Bell Labs for two years. He … Cited by 12 – Related articles – Library Search – All 3 versions

Prosodic and temporal features for language modeling for dialog [PDF] from utep.edu NG Ward, A Vega… – Speech Communication, 2011 – Elsevier … Prosodic and temporal features for language modeling for dialog star, open. … Language modeling can be seen as such a prediction problem, where we need to predict the speaker’s next word, given the previous words and other prior context. … Cited by 5 – Related articles – All 6 versions

Slovak language model from internet text data J Staš, D Hládek, M Pleva… – Toward Autonomous, Adaptive, and …, 2011 – Springer … 1 Introduction The multimodal dialogue system (MMDS) introduces an interaction between the human and computer by various inputs such as speech, writing, face-play, lip movements, etc. … At the end of this paper, future intentions in Slovak language modeling are indicated. … Cited by 4 – Related articles – All 3 versions

Topic tracking language model for speech recognition S Watanabe, T Iwata, T Hori, A Sako… – Computer Speech & …, 2011 – Elsevier … Language Volume 25, Issue 2, April 2011, Pages 440-461 Language and speech issues in the engineering of companionable dialogue systems. … This assumption is not suitable for language modeling since the language model regards a discrete value (word count) as a system … Cited by 5 – Related articles – All 3 versions

Language Modeling with Utterance-Meaning Pairs [PDF] from uni-augsburg.de G WIRSCHING, C Kolbl – Techn. Ber., …, 2011 – opus.bibliothek.uni-augsburg.de … Language modeling is, amongst others, the presentation of a language to a computer, ie, in an algorithmically accessible way. … When designing a speech dialog system, we are not satisfied with an arbitrary language model-what we need is a possibility to extract meaning from … Cited by 1 – Related articles – All 2 versions

[BOOK] Advances in Commercial Deployment of Spoken Dialog Systems D Suendermann – 2011 – books.google.com … 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 … Cited by 2 – Related articles – Library Search – All 2 versions

[PDF] Classifying dialogue in high-dimensional space [PDF] from cmu.edu JP González-Brenes… – Transactions of Speech and …, 2011 – cs.cmu.edu … 2. RELATION TO PRIOR WORK Task-oriented spoken dialogue systems are systems where the user and the computer agent try to accomplish a task together by using spoken language. … In contrast, here we analyze data from a tutorial spoken dialogue system. … Cited by 2 – Related articles – View as HTML – All 6 versions

Bootstrapping semantic parsers from conversations [PDF] from yoavartzi.com Y Artzi… – Proceedings of the Conference on Empirical …, 2011 – dl.acm.org … unannotated conversational logs. We believe that this style of learning will contribute to the long term goal of building self-improving dialog systems that continually learn from their mistakes, with little or no human intervention. … An evaluation on logs from two dialog systems … Cited by 5 – Related articles – All 13 versions

Efficient probabilistic tracking of user goal and dialog history for spoken dialog systems [PDF] from ohio-state.edu A Raux… – Twelfth Annual Conference of the International …, 2011 – isca-speech.org … Computer Studies, vol. 42, pp. 647-666, 1995. [8] A. Raux, N. Mehta, R. Gupta, and D. Ramachandran, “Dy- namic language modeling using bayesian networks for spo- ken dialog systems,” in Proc. Interspeech 2010, 2010. 804 Cited by 1 – Related articles – All 3 versions

Building an automated English sentence evaluation system for students learning English as a second language KJ Lee, YS Choi… – Computer Speech & Language, 2011 – Elsevier … Speech & Language Volume 25, Issue 2, April 2011, Pages 246-260 Language and speech issues in the engineering of companionable dialogue systems. … (2008) introduces an ESL error correction system which utilizes contextual speller techniques and language modeling. … Cited by 2 – Related articles – All 3 versions

Grammatical error detection for corrective feedback provision in oral conversations S Lee, H Noh, K Lee… – Proceedings of the 25th AAAI conference …, 2011 – aaai.org … Raux, A., and Eskenazi, M., 2004. Using task-oriented spoken dialogue systems for language learning: potential, practical applications and challenges. InSTIL/ICALL Symposium, Venice, Italy. … Stolcke, A. 2002. SRILM – An Extensible Language Modeling Toolkit. Proc. Intl. Conf. … Cited by 3 – Related articles – All 3 versions

Speech and multimodal interaction in mobile search [PDF] from ethz.ch J Feng, M Johnston… – Signal Processing …, 2011 – ieeexplore.ieee.org … LANGUAGE MODELING An LM in voice search often have a large vocabulary and, similar to dictation models, have high perplexity … While telephony-based unimodal dialog systems lean toward a more structured interaction where the user and system take well-defined turns and … Cited by 2 – Related articles – All 5 versions

Visual voice mail to text on the iPhone/iPad A Ljolje, V Goffin, D Caseiro… – … Annual Conference of …, 2011 – isca-speech.org … Unlike most dialog systems, it is not the understanding accuracy that determines if a dialog turn was successfully recognized. … This is good for training the punctuation and capitalization components but highly inappropriate for acoustic or language modeling. … Cited by 1 – Related articles – All 2 versions

Document sentiment classification by exploring description model of topical terms Y Hu… – Computer Speech & Language, 2011 – Elsevier … Figures/Tables. Figures/Tables – selected. References. References – selected. Computer Speech & Language Volume 25, Issue 2, April 2011, Pages 386-403 Language and speech issues in the engineering of companionable dialogue systems. … Cited by 5 – Related articles – All 3 versions

Improving spoken dialogue understanding using phonetic mixture models [PDF] from cmu.edu WY Wang, R Artstein, A Leuski… – Proceedings of the Twenty- …, 2011 – aaai.org … Introduction A standard architecture for spoken dialogue systems em- ploys two-tiered processing: An Automatic Speech Recog- nizer (ASR) transforms the … NPCEditor employs a statistical language modeling ap- proach called relevance models (Lavrenko, Choquette, and … Cited by 3 – Related articles – All 8 versions

Understanding considerate systems-UCS (Pronounced: You see us) [PDF] from cmu.edu T Selker – … and Applications of Artificial Intelligence (TAAI), …, 2011 – ieeexplore.ieee.org … Such considerate language modeling will require careful investigation of the tradeoffs between the use of data-rich and … speech recognition, improving speech translation, enabling considerate conversation, moderating and improving spoken dialogue systems, and enabling … Cited by 1 – Related articles – All 6 versions

Constructing n-gram rules for natural language models through exploring the limitation of the Zipf-Mandelbrot law HM Chang – Computing, 2011 – Springer … drama, action, children, etc). There is some non-textual informa- tion in EPG such as the box art for a movie listing. For this paper, we only study textual information for EPG language modeling. The presentation format and distribution … Cited by 2 – Related articles – All 4 versions

Data-driven response generation in social media [PDF] from washington.edu A Ritter, C Cherry… – … of the Conference on Empirical Methods …, 2011 – dl.acm.org … et al., 2001). Currently, most dialogue systems rely on ei- ther canned responses or templates for generation, which can result in utterances which sound very unnatural in context (Chambers and Allen, 2004). Recent work has … Cited by 2 – Related articles – All 12 versions

Automatic speech recognition for polish in a computer game interface [PDF] from eucip.pl A Janicki… – Computer Science and Information …, 2011 – ieeexplore.ieee.org … Another method of approaching language modeling is to build a grammar describing all possible phrases. … It can be treated as a special type of a dialog system, in which in some cases the game may actually predict what the user might want to say, knowing the game scenario. … Cited by 1 – Related articles – All 3 versions

Growing a Spoken Language Interface on Amazon Mechanical Turk [PDF] from mit.edu I McGraw, J Glass… – Twelfth Annual Conference of the …, 2011 – isca-speech.org … Index Terms: organic speech systems, language modeling 1. Introduction … 8(1), 2000. [13] A. Raux, D. Bohus, B. Langner, A. Black, and M. Eskenazi, “Do- ing research on a deployed spoken dialogue system: One year of Let’s Go! … Cited by 1 – Related articles – All 4 versions

Free tools and resources for Brazilian Portuguese speech recognition N Neto, C Patrick, A Klautau… – Journal of the Brazilian …, 2011 – Springer … 2.3 Used tools The HTK software [37] was used to build and adapt the acoustic models presented in this work. The SRI Language Modeling Toolkit (SRILM) was used to build the n-gram ARPA format language models. The … Cited by 4 – Related articles – All 3 versions

Modern standard Arabic speech corpus for implementing and evaluating automatic continuous speech recognition systems MAAM Abushariah, RN Ainon, R Zainuddin… – Journal of the Franklin …, 2011 – Elsevier … In this work, the language model is built statistically using the CMU-Cambridge Statistical Language Modeling toolkit [17], which is based on modeling the uni-grams, bi-grams, and tri-grams of the language for the subject text to be recognized. … Cited by 1 – Related articles – All 2 versions

[BOOK] Statistical Pronunciation Modeling for Non-native Speech Processing RE Gruhn, W Minker… – 2011 – books.google.com … Non-native speech recognition is an important issue in applications such as speech-to-speech translation devices or speech dialog systems. … 1.2 Contribution of this Research The contributions of this work on statistical language modeling of non-native pronunciations to the … Cited by 1 – Related articles – Library Search

Semantic Frame-Based Spoken Language Understanding YY Wang, L Deng… – Spoken Language …, 2011 – Wiley Online Library … project in the 2000s focused on the rapid and cost-effective development of multi-modal speech-enabled dialog systems with advanced … in Figure 3.5 For the LUNA project that focuses on multilingual SLU and language specific aspects for language modeling and understanding … Cited by 1 – Related articles – All 3 versions

[CITATION] P1: LANGUAGE PROCESSING, UNDERSTANDING AND MINING FEBYIS SCALING – ieeexplore.ieee.org … RELATIONSHIPS BETWEEN NAMED ENTITIES TO IMPROVE …..55 SPEECH RECOGNITION IN DIALOG SYSTEMS Shajith Ikbal … PD2.6: QUERY LANGUAGE MODELING FOR VOICE SEARCH …..127 Ciprian Chelba, Johan Schalkwyk …

A Croatian Weather Domain Spoken Dialog System Prototype [PDF] from srce.hr A Meštrovic, L Bernic, M Pobar… – Journal of Computing …, 2011 – hrcak.srce.hr … develop a spoken dialog system for the weather domain. In this paper, we present all specific problems that arise in Croatian language modeling in the process of designing a Croatian weather domain spoken dialog system. … Related articles – All 7 versions

[PDF] Utterance Verification Using Garbage Words for a Hospital Appointment System with Speech Interface [PDF] from yamanashi.ac.jp M Takaoka, H Nishizaki… – alps.cs.yamanashi.ac.jp … and transcriptions for language modeling. In addition, machine learning methods require positive and negative data for training. As described above, the previous research proposals were costly to implement, creating an obstacle for developing a spoken dialog system. … Related articles – View as HTML

Improving ASR processing of ungrammatical utterances through grammatical error modeling [PDF] from unive.it H Strik, J Doremalen, J Loo… – Speech and Language …, 2011 – isca-speech.org … [6] Raux, A., & Eskenazi, M., “Using task-oriented spoken dialogue systems for language learning: Potential practical applications and challenges”, Proc. ISCA ITRW INSTiL04, pp. 147-150. Venice, Italy, 2004. … [8] Van de Loo, J., “Language modeling for ASR-based CALL … Cited by 1 – Related articles – All 2 versions

Detecting levels of interest from spoken dialog with multistream prediction feedback and similarity based hierarchical fusion learning [PDF] from aclweb.org WY Wang… – Proceedings of the SIGDIAL 2011 Conference, 2011 – dl.acm.org … For Spoken Dialog Systems (SDS), the motivation has been to provide users with improved over-the-phone services by recognizing … Discriminative TFIDF approach for lexical modeling and keywords spotting; (2) using lexical affect scoring and language modeling tech- niques … Related articles – All 12 versions

Shrinkage-Based Features for Natural Language Call Routing R Sarikaya, SF Chen… – Twelfth Annual Conference …, 2011 – isca-speech.org … Spoken dialogue systems (SDSs) provide natural access to in- formation and services over the phone … In other words, we would like to discover whether features used by Model M for language modeling are also helpful for classification problems, despite the differences between … Related articles – All 2 versions

[PDF] CONTEXT SPECIFIC LANGUAGE MODELING FOR SPOKEN ROUTE DIRECTIONS [PDF] from cmu.edu A Pappu… – tts.speech.cs.cmu.edu … men- tioned in table 1, using the HUB4_continuous acoustic model in Pocketsphinx[9]. Pocketsphinx is an ASR engine for hand-held de- vices and suitable for a dialogue system that interacts with a mobile robot. We ran different experiments with language modeling using SRI … Related articles – View as HTML – All 2 versions

Combination of stochastic understanding and machine translation systems for language portability of dialogue systems [PDF] from 140.124.72.88 B Jabaian, L Besacier… – Acoustics, Speech and …, 2011 – ieeexplore.ieee.org … [2] K. Suenderman, J. Liscombe, “Localization of speech recognition in spoken dialog systems: How machine translation can make our lives,” in Interspeech 2009. … [14] A. Stolcke, “SRILM an extensible language modeling toolkit,” in SLP 2002. … Cited by 2 – Related articles – All 4 versions

[BOOK] Proceedings of the Paralinguistic Information and Its Integration in Spoken Dialogue Systems Workshop RLC Delgado – 2011 – books.google.com … 14 New Technique for Handling ASR Errors at the Semantic Level in Spoken Dialogue Systems….. … 62 Domain-Adapted Word Segmentation for an Out-of-Domain Language Modeling….. … All 2 versions

[PDF] Semantic information and derivation rules for robust dialogue act detection in a spoken dialogue system [PDF] from aclweb.org WB Liang, CH Wu… – Proceedings of the 49th Annual Meeting …, 2011 – aclweb.org … modeling. Proceedings of the IEEE, 88:1279-1296. N. Fraser and GN Gilbert. 1991. Simulating speech systems. Computer Speech and Language, 5(1):81- 99. C. Hori, K. Ohtake, T. Misu, H. Kashioka, and S. Naka- mura. 2009a. Recent advances in wfst-based dialog system. … Related articles – View as HTML – All 8 versions

[PDF] UNIVERSITÄT AUGSBURG [PDF] from uni-augsburg.de UM Pairs, GJ Wirsching… – informatik.uni-augsburg.de … Language modeling is, amongst others, the presentation of a language to a computer, ie, in an algorithmically accessible way. … When designing a speech dialog system, we are not satisfied with an arbitrary language model-what we need is a possibility to extract meaning from … Related articles – View as HTML – All 2 versions

Speech and mobile technologies for cognitive communication and information systems M Pleva, S Ondas, J Juhar, A Cizmar… – Cognitive …, 2011 – ieeexplore.ieee.org … 553-0644-5, 2011, Slovakia [2] J. Staš, M. Trnka, D. Hládek, and J. Juhár, “Test Preprocessing and Language Modeling for Domain … A. Cižmár, R. Jarina, M. Rusko, G. Rozinaj, “Development of Slovak GALAXY/VoiceXML Based Spoken Language Dialogue System to Retrieve … Related articles

Domain-Adapted Word Segmentation for an Out-of-Domain Language Modeling E Chung, HB Jeon, JG Park… – … in Spoken Dialogue Systems …, 2011 – Springer This paper introduces a domain-adapted word segmentation approach to text where a word  delimiter is not used regularly. It depends on an unknown word extraction technique. This  approach is essential for language modeling to adapt to new domains since a vocabulary … Related articles – All 2 versions

An analysis of machine translation and speech synthesis in speech-to-speech translation system [PDF] from 140.124.72.88 K Hashimoto, J Yamagishi, W Byrne… – … , Speech and Signal …, 2011 – ieeexplore.ieee.org … [7] C. Boidin, V. Rieser, LVD Plas, O. Lemon, and J. Chevelu “Predicting how it sounds: Re-ranking dialogue prompts based on TTS quality for adaptive Spoken Dialogue Systems,” Proc Interspeech, pp … [19] A. Stolcke, “SRILM – An Extensible Language Modeling Toolkit,” Proc … Related articles – All 6 versions

[BOOK] Human Language Technology. Challenges for Computer Science and Linguistics: 4th Language and Technology Conference, LTC 2009, Roznan, Poland, … Z Vetulani – 2011 – books.google.com … The reader will then find a paper on morpheme-based language modeling for speech recognition for Amharic, another less-resourced language … The next two papers cover various aspects of a man-machine dialogue system (POLINT- 112-SMS) designed to understand short … Library Search – All 2 versions

Zanzibar OpenIVR: an open-source framework for development of spoken dialog systems [PDF] from tu-darmstadt.de D Prylipko, D Schnelle-Walka, S Lord… – Text, Speech and …, 2011 – Springer … Zanzibar OpenIVR: A Framework for Development of Spoken Dialog Systems … CMU Sphinx 4 provides numerous capabilities: generalized pluggable frontend and language model architectures, rich capabilities for language modeling, generalized acous- tic model architecture … Related articles – All 10 versions

Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems [PDF] from nagoya-u.ac.jp S Hara, N Kitaoka… – … in Florence, Italy, on August 27 …, 2011 – ir.nul.nagoya-u.ac.jp … 78-83, May 2010. [11] R. Higashinaka and M. Nakano, “Ranking multiple dialogue states by corpus statistics to improve discourse understanding in spoken dialogue systems,” IEICE Trans. … 2009. [13] A. Stolcke, “SRILM – an extensible language modeling toolkit,” in Proc. … Related articles – All 4 versions

SpeechForms: From Web to Speech and Back [PDF] from difabbrizio.com L Barbosa, D Caseiro, GD Fabbrizio… – … Annual Conference of …, 2011 – isca-speech.org … EU- ROSPEECH, 1997. [6] G. Di Fabbrizio et al., “Bootstrapping spoken dialogue systems by exploiting reusable libraries,” Natural Language Engineering, vol. 14, no. 3, pp. 313-335, July 2008. [7] I. Bulyko et al., “Web resources for language modeling in conver- sational … Related articles – All 11 versions

[BOOK] Text, Speech and Dialogue: 14th International Conference, Tsd 2011, Pilsen, Czech Republic, September 1-5, 2011, Proceedings I Habernal… – 2011 – books.google.com … Tomá?s Valenta and Lubo?s ?Smidl Automatic Topic Identification for Large Scale Language Modeling Data Filtering….. … Elzbieta Hajnicz Hierarchical Dialogue System for Guide Robot in Shopping Mall Environments….. … Library Search – All 3 versions

In-Car Media Search ML Seltzer, YC Ju, YY Wang… – Signal Processing …, 2011 – ieeexplore.ieee.org … in-car training data [7]. LANGUAGE MODELING In addition to a properly trained acoustic model, the perfor- mance of a speech-recognition system is critically depen- dent on the quality of its LM. An LM assigns prior probabilities … Related articles – All 5 versions

Broadcast news speech-to-text translation experiments [PDF] from inria.fr S Raybaud, D Langlois, K Smaïli – 2011 – hal.inria.fr … 2000. Algorithms for Statistical Translation of Spoken Language. IEEE Trans. on Speech and Au- dio Processing, Special Issue on Language Modeling and Dialogue Systems, 8:24-36, January. F. Och. 2000. Giza++ tools for training statistical trans- lation models. M. Seligman. … Related articles – All 5 versions

[PDF] Automatic Detection of Unnatural Word-Level Segments in Unit-Selection Speech Synthesis [PDF] from usc.edu WY Wang… – people.ict.usc.edu … This can be very important in applications (eg adaptive spoken dialogue systems) where sentences are generated on the fly. … D. Language modeling Using Delta TF-IDF, we are able to model the lexical cues and rare terms in the training and testing data sets. … Related articles – View as HTML – All 4 versions

Investigating the role of machine translated text in ASR domain adaptation: Unsupervised and semi-supervised methods H Cucu, L Besacier, C Burileanu… – … Speech Recognition and …, 2011 – ieeexplore.ieee.org … to properly create annotated speech corpora for automatic speech recognition (ASR), domain-specific text corpora for language modeling (LM), tagged … Several approaches for language portability (French to Italian) of dialogue systems are being investigated in [5]. In a previous …

CRF, 50 CUDA, 196, 199 CURD, 262 CV classification, 42 CV-dependent Wiener filter, 42 C Computing… – … in Spoken Dialogue Systems …, 2011 – books.google.com … Integration, 126 Intention recognizer, 166 Interaction paramter, 219 Interactive voice response, 241 IPA, 257 Italian children ASR, 128 Iterative design, 271 Joint source-channel, 53 Keyword accuracy, 344 Language modeling, 63 Language tutoring dialog systems, 213 LARRI …

Real-life speech-enabled system to enhance interaction with rfid networks in noisy environments [PDF] from 140.124.72.88 Y Benahmed, SA Selouani… – … , Speech and Signal …, 2011 – ieeexplore.ieee.org … In this paper, we present an effective framework for interactive spoken dialog systems belonging to the third category, using a dy- namic … Improving command and control speech recognition on mobile devices: using predictive user models for language modeling,” User Modeling … Cited by 1 – Related articles – All 3 versions

[PDF] Semantic class induction and its application for a Chinese voice search system [PDF] from aclweb.org W Xu… – aclweb.org … 1 Introduction Voice search (eg Wang et al., 2008) has recently become one of the major foci in spoken dialogue system research and development. … But for a voice search system, we have to deal with the case where there is no or very little relevant data for language modeling. … Related articles – View as HTML – All 6 versions

Bayesian Language Model Interpolation for Mobile Speech Input [PDF] from nyu.edu C Allauzen… – Twelfth Annual Conference of the …, 2011 – isca-speech.org … 93-96. [11] K. Visweswariah and H. Printz, “Language models conditioned on dialogue state,” in Proc. of EUROSPEECH, 2001, pp. 251-254. [12] W. Xu and A. Rudnicky, “Language modeling for dialog system,” in Proc. of ICSLP, 2000, pp. 118-121. … Related articles – All 5 versions

Real-time large vocabulary spontaneous speech recognition for spoken dialog systems [PDF] from zcu.cz J Svec… – Image and Signal Processing (CISP), 2011 …, 2011 – ieeexplore.ieee.org … languages where the formal written language and a common colloquial speech are very different. The overall word error rate was reduced by 16.7%. Index Terms-speech recognition, language modeling, spoken dialog system … Related articles – All 3 versions

[PDF] Syntactic Approaches for Natural Language Processing [PDF] from videolectures.net JA Sánchez – videolectures.net … Applications Automatic Speech Recognition Machine Translation Dialog Systems Automatic Summarization Text Classification Information Retrieval … Abstract tasks Language Modeling Part of Speech Tagging Parsing Lexical Disambiguation Semantic Analysis … Related articles – View as HTML

Candidate Generation for ASR Output Error Correction Using a Context-Dependent Syllable Cluster-Based Confusion Matrix CH Liu, CH Wu, D Sarwono… – Twelfth Annual Conference …, 2011 – isca-speech.org … [3] Liu, C.-H., Wu, C.-H., and Harris, M., “Word Order Correction for Language Transfer using Relative Position Language Modeling,” in Proceedings … [6] Sagawa, H., Mitamura, T., and Nyberg, E., “Correction grammars for error handling in a speech dialog system,” in Proceedings … Related articles – All 2 versions

Incremental Learning and Forgetting in Stochastic Turn-Taking Models [PDF] from cmu.edu K Laskowski, J Edlund… – Twelfth Annual Conference of …, 2011 – isca-speech.org … [3] Raux, A. and Eskenazi, M., “Finite state turn taking model for spoken dialog systems”, Proc HLT … doi:10.1016/S0065- 2601(08)60413-X [12] Chen, S. and Goodman, J., “An empirical study of smoothing techniques for language modeling”, Tech Report TR-10-98, Har- vard … Cited by 1 – Related articles – All 5 versions

Pronunciation Learning from Continuous Speech [PDF] from mit.edu I Badr, I McGraw… – Twelfth Annual Conference of the …, 2011 – isca-speech.org … pronunciation mixture model framework to two domains containing spontaneous speech: a weather information retrieval spoken dialogue system and the … independence assumptions, the first is similar to the Markov assumption made in n-gram language modeling, the second … Related articles – All 4 versions

[CITATION] Kikuo Maekawa SS Agrawal, B Michailovsky, A Michaud… – ieeexplore.ieee.org … P.97 Spoken Dialog System Ryosuke Inoue, Yoshiaki Kurosawa, Kazuya Mera and Toshiyuki Takezawa … Pt 06 Haipeng Wang, Tan Lee and Cheung-Chi Leung Morpheme Concatenation Approach in Language Modeling for Large-Vocabulary P.tt2 …

[PDF] Précis of Thesis: A Broad-Coverage Model of Prediction in Human Sentence Processing [PDF] from uni-saarland.de V Demberg-Winterfors – coli.uni-saarland.de … a text (such systems can be used in automatic readability assessments) and optimisation of machine-generated text or speech (for example in symmetrisation, translation, tutoring systems and general dialogue systems). … Probabilistic top-down parsing and language modeling. … Related articles – View as HTML – All 3 versions

A large vocabulary continuous speech recognition system for Persian language [PDF] from eurasipjournals.com H Sameti, H Veisi, M Bahrani, B Babaali… – EURASIP Journal on …, 2011 – Springer … system, acoustic modeling is based on hidden Markov models, and optimized decoding, pruning and language modeling techniques were used in … In the last decade, researchers and investors introduced spoken dialogue systems and tried to implement conversational speech … Related articles – All 3 versions

[PDF] Similarity Based Language Model Construction for Voice Activated Open-Domain Question Answering [PDF] from univ-mlv.fr I Varga, K Ohtake, K Torisawa, S De Saeger… – igm.univ-mlv.fr … 5.1 Evaluation settings 5.1.1 Corpora We prepared two Web archives as the starting point of language modeling: the first (www) is unfiltered in regards of style, while the second (wwwq) is a subset of the first, attempting to fol- low the style requirements of the QA system. … Related articles – View as HTML – All 7 versions

Automatic fingersign-to-speech translation system M Hrúz, P Campr, E Dikici, AA Kindiroglu… – Journal on Multimodal …, 2011 – Springer … continuous speech recogni- tion (LVCSR) systems have become available for Turkish broadcast news transcription [6]. An HTK based version of this system is also available [8]. LVCSR systems for agglu- tinative languages typically use sub-word units for language modeling. … Related articles – All 2 versions

SICE: An Enhanced Framework for Design and Development of Speech Interfaces on Client Environment [PDF] from ijcaonline.org V Prabhat, S Raghuraj… – International Journal of …, 2011 – ijcaonline.org … lines; the SRGS offers support for speech recognition; the CCXML provides telephony call control support and other dialog systems, while the … Then, it uses language modeling (the likelihood that a given word appears between those coming before and after it) to narrow the list … Related articles – All 2 versions

Introducing Language Technology & Computational Linguistics in Bangladesh [PDF] from ccsenet.org M Rashel – International Journal of English Linguistics, 2011 – ccsenet.org … Pronunciation Generator, Morphological Analysis, Parts of Speech Tagging, Syntax, Grammar Checker, Text Categorization, Language Modeling and many … such as developing a local language dialect and indigenous language database and customized dialog system for easy … Related articles – All 3 versions

[PDF] 1 Successful Conclusion of the 2010 Summer Workshop [PDF] from jhu.edu J Du – old-site.clsp.jhu.edu … Discriminative n-gram language modeling. … The development of more controllable emotion speech synthesis is necessary in the improvement of human machine communication in spoken dialog systems, speech to speech translation systems and any device offering speech … Related articles – View as HTML – All 4 versions

Efficient Use of Voice Activity Detector and Automatic Speech Recognition in Embedded Platforms for Natural Language Interaction M Santos-Pérez, E González-Parada… – Highlights in Practical …, 2011 – Springer … 3 Efficient Use of VAD and ASR In a typical spoken dialog system the ASR processes the full utterances obtained by the VAD. … Zhang, J., Ward, W., Pellom, B., Yu, X., Hacioglu, K.: Improvements in audio process- ing and language modeling in the CU communicator. … Related articles – All 2 versions

Introduction to Arabic Natural Language Processing Nizar Y. Habash (Columbia University) Morgan & Claypool (Synthesis Lectures on Human Language … I Zitouni – Computational Linguistics, 2011 – MIT Press … He received his M.Sc. and Ph.D. from the University of Nancy 1 in 1996 and 2000, respectively. His research interests include language modeling, information extraction, machine translation, machine learning, and spoken dialogue systems; e-mail: izitouni@us.ibm.com. 625 Related articles

[PDF] Croatian Large Vocabulary Automatic Speech Recognition [PDF] from srce.hr S Martincic-Ipšic, M Pobar… – AUTOMATIKA, 2011 – hrcak.srce.hr … mental results encourage the use of the proposed LVASR system for spontaneous Croatian speech applications like spoken dialog systems. … of the speech recognition system in- cluding phonetically driven state tying procedures as well as language modeling methods are … Related articles – View as HTML – All 5 versions

Confidence Measures for Turkish Call Center Conversations A Haznedaroglu… – Twelfth Annual Conference of the …, 2011 – isca-speech.org … Semantic confidence measurement for spoken dialog systems. IEEE Transactions on Speech and Audio Processing, vol. … [11] Clarkson, P., Rosenfeld, R., 1997. Statistical Language Modeling Using the CMU-Cambridge Toolkit from Proceedings ESCA. … Related articles – All 2 versions

[PS] A Hybrid Language Understanding Approach for Robust Selection of Tutoring Goals [PS] from cmu.edu R Srivastava… – cs.cmu.edu … 2001. Initiative management for tutorial dialogue. In Proceedings of the NAACL Workshop Adaption in Dialogue Systems. 5] MS Glass. 1999. … 1996. Bow: A toolkit for statistical language modeling, text retrieval, classi cation and clustering. http://www.cs.cmu.edu/ mccallum/bow. … Related articles – View as HTML – All 2 versions

Towards a conversational agent architecture to favor knowledge discovery in serious games F Bellotti, R Berta, A De Gloria… – Proceedings of the 8th …, 2011 – dl.acm.org … The problem of implementing a dialogue system may be tackled also in terms of text retrieval. … probability model adds to the TF-IDF basic statistics several parameters for tuning on development data [11].Another approach, similar to TF-IDF, relies on language modeling (LM) [12 ... Related articles

Recognition of Multiple Language Voice Navigation Queries in Traffic Situations [PDF] from bme.hu G Sárosi, T Mozsolics, B Tarján, A Balog… – Analysis of Verbal and …, 2011 – Springer … language pre-selection. One of the leading companies in speech technology Google has recently pub- lished a study [1] about the language modeling approaches applied in their “Search by voice” service. In this study they … Cited by 1 – Related articles – All 3 versions

[PS] PERMUGRAM LANGUAGE MODELS [PS] from uni-jena.de G Ernst – minet.uni-jena.de … Abstract In natural languages, the words within an utterance are often correlated over large dis- tances. Long-spanning contextual e ects of this type cannot be e ciently and robustly cap- tured by the traditional N-gram approaches of stochastic language modeling. … Related articles – View as HTML – All 4 versions

Intelligent Tutoring Systems A Keles… – 2011 – igi-global.com … of target vocabulary. The tutor uses an extended version of the Lemur Toolkit for Language Modeling and Information Retrieval to annotatethe documents and create an index for language-model based retrieval. When a student … Related articles – All 3 versions

Robustness of Automatic Speech Recognition SA Selouani – Speech Processing and Soft Computing, 2011 – Springer … pragmatic knowledge from pronounced utterances. The problem of ASR robustness and efficiency of spoken dialog systems is addressed in the following sections. 6.2 Speech Recognition Problem ASR methods build speech …

Trends, Challenges and Opportunities in Spoken Dialogue Research M McTear – Spoken Dialogue Systems Technology and Design, 2011 – Springer … Following this some chal- lenges are identified, in particular, the issues faced by individual researchers and those in small groups who wish to build viable end-to-end dialogue systems and the difficulties that are often encountered by academic researchers when research. … Related articles

[PDF] Temporal Distributional Analysis [PDF] from utep.edu NG Ward – cs.utep.edu … neighbors are sim- ilar. New aspects of similarity may support better methods for dimensionality reduction for the lexi- con, which in turn is critical for tasks from language modeling to information retrieval. Regardless of the existence … Related articles – View as HTML – All 2 versions

UT-Scope: Towards LVCSR under Lombard effect induced by varying types and levels of noisy background [PDF] from ed.ac.uk H Boril… – Acoustics, Speech and Signal …, 2011 – ieeexplore.ieee.org … Model Toolkit (HTK) based acoustic modeling and trigram language model (LM) implemented with the SRI Language Modeling Toolkit (SRILM … and R. López-Cózar, “Influence of contextual information in emotion annotation for spoken dialogue systems,” Speech Communication … Cited by 1 – Related articles – All 10 versions

[PDF] Survey on Speech, Machine Translation and Gestures in Ambient Assisted Living [PDF] from uni-sb.de D Anastasiou – ai.cs.uni-sb.de … recognition and synthesis, and Machine Translation (MT); speech-to-speech translation, dialog systems, and gesture recognition and localization will also be … It should be pointed out that language modeling is not related only to speech recognition, but also MT, PoS-tagging and … Related articles – View as HTML – All 2 versions

Modeling of non-native speech automatic speech recognition [PDF] from nus.sg X YUANTING – 2011 – scholarbank.nus.sg … address these challenges. The ASR consists of three parts, acoustic modeling, lexical modeling and language modeling. In the thesis, the author will first give a brief introduction of the research topic and the work has been done in chapter 1. In chapter 2, … Related articles – All 3 versions

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

Self-learning speaker identification for enhanced speech recognition T Herbig, F Gerl… – Computer Speech & Language, 2011 – Elsevier … The Viterbi algorithm (Rabiner and Juang, 1993) is applied to determine the most likely word string. More details on generic language modeling can be found in Manning and Schütze (1999). 4. Speaker adaptation. Statistical … Related articles – All 2 versions

[PDF] Design and evaluation of acceleration strategies for speeding up the development of dialog applications [PDF] from upm.es LF D’Haro, R De Cordoba… – Speech …, 2011 – www-gth.die.upm.es … will refer, like in the dialog and auto- mata theory, to one of all the possible nodes or states in a finite state based dialog system. … The second one is the Language Modeling Toolkit that allows the designer to specify and debug the grammar files (in JSGF format or n-gram based … Related articles – View as HTML – All 4 versions

[PDF] Exploring Speech Technologies for Language Learning [PDF] from intechopen.com R Delmonte – 2011 – intechopen.com Page 1. 5 Exploring Speech Technologies for Language Learning Rodolfo Delmonte Università Ca’ Foscari – Ca’ Bembo, Linguistic Computational Laboratory, Italy 1. Introduction The teaching of the pronunciation of any foreign … Related articles – View as HTML – All 3 versions

Experiments on Cross-Language Attribute Detection and Phone Recognition with Minimal Target-Specific Training Data S Siniscalchi, D Lyu, T Svendsen… – Audio, Speech, and … – ieeexplore.ieee.org Page 1. Copyright (c) 2011 IEEE. Personal use is permitted. For any other purposes, permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Related articles

History of Knowledge and Processes for Spoken Language Understanding R De Mori – Spoken Language Understanding, 2011 – Wiley Online Library Page 1. Part 1 Spoken Language Understanding for Human/Machine Interactions Spoken Language Understanding: Systems for Extracting Semantic Information from Speech, First Edition. Edited by Gokhan Tur and Renato De Mori. (c) 2011 John Wiley & Sons, Ltd. … Related articles – All 2 versions

Index-based incremental language model for scalable directory assistance A Moreno-Daniel, J Wilpon… – Speech Communication, 2011 – Elsevier … 1. Introduction Voice search enables an informational spoken dialog system (SDS) to find a ranked list of database entries relevant to an … 3.3.4. Incremental language models and on-the-fly re-scoring Incremental language modeling [11, 40, 18, 17] is a decoding strategy that is … Related articles – All 2 versions

[HTML] Survey on Speech, Machine Translation and Gestures in Ambient Assisted Living. http://webcast. in2p3. fr/old/2011/tralogy/index. php? video= anastasiou. … [HTML] from inist.fr D Anastasiou – 2011 – lodel.irevues.inist.fr … of-the-art tools1 of speech recognition and synthesis, and Machine Translation (MT); speech-to-speech translation, dialog systems, and gesture … It should be pointed out that language modeling is not related only to speech recognition, but also MT, PoS-tagging and Information … Related articles – Cached – All 2 versions

[PDF] Enhancement of Conversational Agents by Means of Multimodal Interaction [PDF] from ugr.es R López-Cózar, Z Callejas, G Espejo… – Conversational Agents and …, 2011 – ugr.es Page 1. 223 Copyright (c) 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. Chapter 10 DOI: 10.4018/978-1-60960- 617-6.ch010 Ramón López-Cózar University of Granada, Spain … View as HTML – All 5 versions

Large-scale latent semantic analysis [PDF] from memphis.edu AMG Olney – Behavior research methods, 2011 – Springer Page 1. Large-scale latent semantic analysis Andrew McGregor Olney Published online: 8 February 2011 (c) Psychonomic Society, Inc. 2011 Abstract Latent semantic analysis (LSA) is a statistical technique for representing word … Related articles – All 4 versions

My science tutor: A conversational multimedia virtual tutor for elementary school science [PDF] from bltek.com W Ward, R Cole, D Bolaños… – ACM Transactions on …, 2011 – dl.acm.org … While spoken dialogue systems have been developed for science tutoring for university-level students, and for children for reading and lan- guage assessment, we have no evidence of intelligent tutoring systems that support spoken conversational interaction between children … Cited by 8 – Related articles – All 3 versions

[BOOK] Extraction and Representation of Prosody for Speaker, Speech and Language Recognition L Mary – 2011 – books.google.com … 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 2 versions

[PDF] Automatic analysis of multiparty meetings [PDF] from ias.ac.in S Renals – Sadhana, 2011 – ias.ac.in … until the mid-1990s virtually all research was focused on dictation, command and control applications, and human-computer spoken dialogue systems. … Wesley) Bulyko I, Ostendorf M, Siu M, Ng T, Stolcke A, Cetin O 2007 Web resources for language modeling in conversational … Related articles – View as HTML – All 4 versions

Towards an architecture for personalized information retrieval implying the user’s profile and votes [PDF] from archives-ouvertes.fr A Harbaoui, S Sidhom, M Ghenima… – 2011 – hal.archives-ouvertes.fr … Diverse types of query languages have been proposed in the literature: ? List of keywords: SMART system and OKAPI [3], [10] ? Natural language: SMART system and SPIRIT [4] ? Boolean language: DIALOG system [5] ? Graphic language: NEURODOC [4] The principle goal of … Related articles – All 3 versions

Grounding of Word Meanings in Latent Dirichlet Allocation-Based Multimodal Concepts [PDF] from nict.go.jp T Nakamura, T Araki, T Nagai… – Advanced Robotics, 2011 – ingentaconnect.com Page 1. Advanced Robotics 25 (2011) 2189-2206 brill.nl/ar Full paper Grounding of Word Meanings in Latent Dirichlet Allocation-Based Multimodal Concepts Tomoaki Nakamura a,* , Takaya Araki a, Takayuki Nagai a and … Related articles – All 2 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 4 versions

Round-robin duel discriminative language models in one-pass decoding with on-the-fly error correction [PDF] from 140.124.72.88 T Oba, T Hori, A Ito… – Acoustics, Speech and …, 2011 – ieeexplore.ieee.org … In online applications such as spoken dialog systems, speech recognizers need to work in real time and with low latency not to prevent smooth human … [1] Brian Roark, Murat Saraclar, Michael Collins, and Mark Johnson, “Discriminative language modeling with conditional … Related articles – All 3 versions

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

[PDF] FUNCTION AND REALIZATION OF HUNGARIAN DISFLUENCIES [PDF] from isphs.org V Horváth – … SCIENCES (ISPHS): ADDRESSES www. isphs. org – isphs.org … speaking style and voice modeling for speaker mimic, finite-state syntactic processing models for natural language, discriminative syntactic language modeling, automated recognition of emotion from speech, mixed-initiative dialogue systems, modeling coarticulation for speech … Related articles – View as HTML

A Kernel Framework for Content-Based Artist Recommendation System in Music Z Chen, J Jang… – Multimedia, IEEE Transactions on, 2011 – ieeexplore.ieee.org Page 1. Copyright (c) 2011 IEEE. Personal use is permitted. For any other purposes, permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Cited by 1 – Related articles – All 2 versions

[PDF] Improved Statistical Machine Translation Using MultiWord Expressions [PDF] from ehu.es D Bouamor, N Semmar… – LIHMT 2011, 2011 – ixa2.si.ehu.es … We also specified two language models using the IRST Language Modeling Toolkit 3 to train two tri-gram models. … Proceedings of the 4th Interna- tional Conference on Speech and Dialogue Systems, Iasi, Romania, p. 183-195. Vechtomova O.(2005). … Related articles – View as HTML – All 2 versions

Utilizing gestures to improve sentence boundary detection [PDF] from jhu.edu L Chen… – Multimedia Tools and Applications, 2011 – Springer … It also would support many language processing tasks such as parsing, language modeling, and question answering in dialog systems. Due to its importance, much research has been conducted on sentence boundary detection [32, 34, 45, 47, 48]. … Related articles – All 8 versions

Standard audio format encapsulation (SAFE) [PDF] from unila.ac.id H Beigi… – Telecommunication Systems, 2011 – Springer … at the IBM TJ Watson Research Center from 1991 to 2001 where he conducted research on Speaker Recognition, Language Modeling, Aggressive Search … In D. Dahl (Ed.), Practical Spoken Dialog Systems and two articles in the SZ Li (Ed.), Encyclopedia of Biometrics), journal … Cited by 1 – Related articles – All 6 versions

[BOOK] Cross-Word Modeling for Arabic Speech Recognition [PDF] from springer.de D Abuzeina… – 2011 – books.google.com … 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 … Cao et al. (2005) proposed an approach to extend the existing language modeling approach by … Related articles – All 4 versions

The subspace Gaussian mixture model–A structured model for speech recognition [PDF] from cvut.cz D Povey, L Burget, M Agarwal, P Akyazi… – Computer Speech & …, 2011 – Elsevier … Figures/Tables. Figures/Tables – selected. References. References – selected. Computer Speech & Language Volume 25, Issue 2, April 2011, Pages 404-439 Language and speech issues in the engineering of companionable dialogue systems. … Cited by 18 – Related articles – All 8 versions

[PDF] Discriminative Reranking for Spoken Language Understanding [PDF] from unitn.it M Dinarelli, A Moschitti… – 2011 – disi.unitn.it Page 1. IEEE TRANSACTION ON SPEECH AND LANGUAGE PROCESSING 1 Discriminative Reranking for Spoken Language Understanding Marco Dinarelli, Alessandro Moschitti, and Giuseppe Riccardi, Fellow, IEEE Abstract … Related articles – View as HTML – All 3 versions

Named Entity Recognition F Béchet – Spoken Language Understanding, 2011 – Wiley Online Library … In NER from speech, the SLU module of Spoken Dialogue Systems (SDS) often relies on the detection and extraction of application-specific entities such as telephone numbers or customers’ names. … 10.1.3.2 Spoken Dialogue Systems … Cited by 1 – Related articles – All 2 versions

Medical data mining: Improving information accessibility using online patient drug reviews [PDF] from 18.7.29.232 S Seneff, YA Li – 2011 – 18.7.29.232 … 2.2.1 Dialogue Systems Personalized medical systems often implement a dialogue system that aims to simu- late or supplement the expertise of health care providers [46]. … Speech recog- nition and language modeling are also challenges faced in this and other constrained … Cited by 2 – Related articles – All 3 versions

Phonetically rich and balanced text and speech corpora for Arabic language MAM Abushariah, RN Ainon, R Zainuddin… – Language Resources …, 2011 – Springer Page 1. ORIGINAL PAPER Phonetically rich and balanced text and speech corpora for Arabic language Mohammad AM Abushariah · Raja N. Ainon · Roziati Zainuddin · Moustafa Elshafei · Othman O. Khalifa (c) Springer Science+Business Media BV 2011 … Related articles

Bayesian Networks for Discrete Observation Distributions in Speech Recognition A Miguel, A Ortega, L Buera… – Audio, Speech, and …, 2011 – ieeexplore.ieee.org … of this family of techniques in the speech community, good performances have been obtained when used as an alternative to the HMM independence assumption, [12], to model the covariance ma- trix structure [13], [14], for language modeling [15] or in dialog systems [16]. … Cited by 2 – Related articles – All 2 versions

Mining association language patterns using a distributional semantic model for negative life event classification LC Yu, CL Chan, CC Lin… – Journal of Biomedical Informatics, 2011 – Elsevier … A dialog system could generate supportive responses if it could understand the negative life events embedded in users input. Therefore, this study proposes a framework for negative life event identification. … [9] Chien JT. Association pattern language modeling. IEEE Trans. … Related articles – All 3 versions

Evaluation and Optimisation of Incremental Processors [PDF] from elanguage.net T Baumann, O Buß… – Dialogue & Discourse, 2011 – elanguage.net … Incremental spoken dialogue systems, which process user input as it unfolds, pose additional engineering challenges compared to more standard non-incremental systems: Their processing components must be able to accept partial, and possibly subsequently revised input … Cited by 3 – Related articles – All 14 versions

Pronunciation modeling for large vocabulary speech recognition [PDF] from illinois.edu A Kantor – 2011 – ideals.illinois.edu … iv Page 6. Chapter 4 LANGUAGE MODELING . . . . . … able for a variety of specialized tasks, such as small vocabulary and restricted grammar dialog systems, and even dictated speech [67]. However, accurate recognition of spontaneous conversational speech remains elusive. … Cited by 1 – Related articles – All 7 versions

[PDF] Exploiting Distance Based Similarity in Topic Models for User Intent Detection [PDF] from officelive.com A Celikyilmaz, D Hakkani-Tur, G Tur, A Fidler… – gokhantur.tech.officelive.com … Spoken Language Understanding (SLU), a component of spoken dialogue systems, has been an active research area, in which the aim is to extract semantic meaning, such as speaker intention … [7] M. Saraclar and B. Roark, “Joint discriminitive language modeling and utterance … Related articles – View as HTML

Production of filled pauses in concatenative speech synthesis based on the underlying fluent sentence J Adell, D Escudero… – Speech Communication, 2011 – Elsevier … Today, however, the various applications of text- to-speech (TTS) systems (eg, video-games, robotics, dialogue systems, audiovisual production, multilingual broadcasting and automatic film dubbing) demand a va- riety of styles. … Cited by 1 – Related articles – All 2 versions

Preference Music Ratings Prediction Using Tokenization and Minimum Classification Error Training J Reed… – Audio, Speech, and Language Processing, …, 2011 – ieeexplore.ieee.org Page 1. Copyright (c) 2011 IEEE. Personal use is permitted. For any other purposes, Permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Related articles – All 2 versions

Unsupervised Segmentation of Human Motion Data Using a Sticky Hierarchical Dirichlet Process-Hidden Markov Model and Minimal Description Length-Based … [PDF] from nict.go.jp T Taniguchi, K Hamahata… – Advanced Robotics, 2011 – ingentaconnect.com Page 1. Advanced Robotics 25 (2011) 2143-2172 brill.nl/ar Full paper Unsupervised Segmentation of Human Motion Data Using a Sticky Hierarchical Dirichlet Process-Hidden Markov Model and Minimal Description Length-Based Chunking Method for Imitation Learning … Related articles – All 2 versions

[PDF] Predicting, detecting and explaining the occurrence of vocal activity in multi-party conversation [PDF] from cmu.edu K Laskowski – 2011 – cs.cmu.edu Page 1. Predicting, Detecting and Explaining the Occurrence of Vocal Activity in Multi-Party Conversation Kornel Laskowski CMU-LTI-11-001 February 2011 Language Technologies Institute School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 … Cited by 3 – Related articles – View as HTML – All 12 versions

A statistical confidence measure framework for probabilistic parsing [PDF] from upv.es R SÁNCHEZ SÁEZ – 2011 – riunet.upv.es … Parsing plays an important role in problems like Semantic Analysis, Question Answering, Language Modeling [9, 32], Machine Translation [40, 7], RNA … have been successfully applied in the mentioned tasks of ASR [39, 34], SMT [38], and even Spoken Dialogue Systems [33]. … Related articles

Equivalence of Generative and Log-Linear Models G Heigold, H Ney, P Lehnen… – Audio, Speech, and …, 2011 – ieeexplore.ieee.org Page 1. Copyright (c) 2010 IEEE. Personal use is permitted. For any other purposes, Permission must be obtained from the IEEE by emailing pubs-permissions@ieee.org. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. … Cited by 1 – Related articles – All 2 versions

A Regularized Maximum Figure-of-Merit (rMFoM) Approach to Supervised and Semi-supervised Learning C Ma… – Audio, Speech, and Language Processing, …, 2011 – ieeexplore.ieee.org Page 1. Copyright (c) 2010 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. … Related articles – All 2 versions

Correction of Noisy Sentences using a Monolingual Corpus [PDF] from arxiv.org D Chatterhee – Arxiv preprint arXiv:1105.4318, 2011 – arxiv.org … List of Tables iv List of Algorithms v 1 Introduction 1 1.1 Language Modeling . . . . . … somehow. Such Natural Language Generation is performed by a number of applications like Machine Translation, Question Answering, Dialog Systems, 1 Page 13. Summarization systems etc. … Related articles – All 3 versions

A Data-Driven Affective Analysis Framework Toward Naturally Expressive Speech Synthesis J Bellegarda – Audio, Speech, and Language Processing, …, 2011 – ieeexplore.ieee.org … When it comes to man-machine communication, it is thus highly desirable to take account of emotional states as an integral part of human-computer interaction, at both input and output levels [2]. If a spoken dialog system could reliably determine that a user is upset or annoyed … Related articles – All 3 versions

Semantic and phonetic automatic reconstruction of medical dictations S Petrik, C Drexel, L Fessler, J Jancsary… – Computer Speech & …, 2011 – Elsevier … Figures/Tables. Figures/Tables – selected. References. References – selected. Computer Speech & Language Volume 25, Issue 2, April 2011, Pages 363-385 Language and speech issues in the engineering of companionable dialogue systems. … Related articles – All 3 versions

Automatic Speech Recognition for ageing voices [PDF] from ed.ac.uk R Vipperla – 2011 – era.lib.ed.ac.uk … Springer, 2009. (Chapter 4) • Maria Wolters, Ravichander Vipperla, and Steve Renals. Age Recognition for Spoken Dialogue Systems: Do We Need It? In Proceedings of Interspeech, Brighton, 2009. (Chapter 7) • Ravichander Vipperla, Steve Renals, and Joe Frankel. … Related articles – All 5 versions

Linguistic Structure Prediction [PDF] from cmu.edu NA Smith – Synthesis Lectures on Human Language …, 2011 – 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 6 – Related articles – Library Search – All 6 versions

[PDF] LEARNING SUB-WORD UNITS AND EXPLOITING CONTEXTUAL INFORMATION FOR OPEN VOCABULARY SPEECH RECOGNITION [PDF] from jhu.edu MC Parada – 2011 – old-site.clsp.jhu.edu … always went out of their way to explain things to me and share tools. Thank you to Denis Filimonov from University of Maryland for collaborating with me and sharing his language modeling and POS tools for some of the experiments presented in Chapter 4. … Related articles – View as HTML – All 2 versions

[BOOK] Handbook of natural language processing and machine translation: DARPA global autonomous language exploitation J Olive – 2011 – books.google.com … For dictation, WER above 10 percent is not acceptable, but for a dialogue system, a much higher rate can be tolerated as long as the system can enable a user to complete a specific task successfully. … 183 2.5 Language Modeling for SMT … Cited by 6 – Related articles – Library Search – All 5 versions

Characterizing phonetic transformations and fine-grained acoustic differences across dialects [PDF] from mit.edu JP Campbell, NFY Chen – 2011 – dspace.mit.edu Page 1. Characterizing Phonetic Transformations and Fine-Grained Acoustic Differences Across Dialects by MASSACHUSETTS INST OF TECHNOLOGY Nancy Fang-Yih Chen BS, National Taiwan University (2002) 8 2011 SM, National Taiwan University (2004) LIBRARIES … Related articles

cROVER: Context-augmented Speech Recognizer based on Multi-Decoders’ Output [PDF] from uwaterloo.ca MK Abida – 2011 – uwspace.uwaterloo.ca … 7 2.1.3 Language Modeling . . . … HM Harmonic Mean HMM Hidden Markov Model LM Language Modeling or Model LSI Latent Semantic Indexing LVCSR Large Vocabulary Continuous Speech Recog- nition MR Mean Rank of the Semantic Scores MSS Mean Semantic Scoring … Related articles – All 5 versions

[BOOK] Speech Processing and Soft Computing SA Selouani – 2011 – books.google.com Page 1. SPRINGER BRIEFS IN SPEECH TE(HNOLOGY S|d Ahmed Se|0uan| Speech Process|ng and Soft Computing @ Springer Page 2. SpringerBriefs in Electrical and Computer Engineering For further volumes: www.springer.com/series/10059 Page 3. Page 4. … Related articles

[PDF] An Architecture for Scalable, Universal Speech Recognition [PDF] from cmu.edu DH Daines – lti.cs.cmu.edu … sets. The motivation for this work was to allow a speech recognition engine to be used as a “black box” in a variety of spoken dialog systems, that is, without requiring customized language and acoustic models for every domain. … Related articles – View as HTML – All 4 versions

[PDF] Automatic Dialect and Accent Recognition and its Application to Speech Recognition [PDF] from columbia.edu F Biadsy – 2011 – academiccommons.columbia.edu … 28 5.1 Parallel phone recognition followed by language modeling (Parallel PRLM) for dialect recognition. . . . … It should also prove useful in telephony-based help systems, either adapt- ing the output of text-to-speech synthesis in a spoken dialogue system to produce regional … Cited by 2 – Related articles – View as HTML – All 3 versions

Pronunciation learning for automatic speech recognition [PDF] from mit.edu J Glass, I Badr – 2011 – dspace.mit.edu … Building on the work of the previous chapter, we extend our framework to two domains contain- ing spontaneous speech: a weather information retrieval spoken dialogue system and an academic lectures domain. We find that our learned lexicons out-perform expert, … Related articles – All 3 versions

[PDF] Social Network Analysis for Automatic Role Recognition [PDF] from epfl.ch S Favre – 2011 – biblion.epfl.ch Page 1. POUR L’OBTENTION DU GRADE DE DOCTEUR ÈS SCIENCES acceptée sur proposition du jury: Prof. P. Vandergheynst, président du jury Prof. H. Bourlard, Dr A. Vinciarelli, directeurs de thèse Dr F. Pianesi, rapporteur Prof. S. Renals, rapporteur Prof. J.-Ph. … Related articles – Library Search – All 5 versions

Managing misspelled queries in IR applications [PDF] from grupolys.org J Vilares, M Vilares… – Information Processing & Management, 2011 – Elsevier … Many information retrieval (IR) applications such as information extraction, question answering and dialog systems require user queries to be … and Matsuda, 1999] ), divergence from randomness (Vilares, Oakes, & Vilares, 2008) or statistical language modeling ( [McNamee and ... Related articles - All 6 versions

[PDF] ROILA [PDF] from drhu.eu O Mubin – drhu.eu Page 1. Robot Interaction Language Omar Mubin ROILA Page 2. ROILA RObot Interaction LAnguage Omar Mubin Page 3. Page 4. ROILA: RObot Interaction LAnguage PROEFONTWERP ter verkrijging van de graad van doctor … Related articles – View as HTML

[PDF] ” Cheng yu da ci dian” bian wei hui.(????). Cheng yu da ci dian. Beijing, Shang wu yin shu guan guo ji you xian gong si.** Ajam, R. q.(????). Maws¿±** at mu* ¹* … [PDF] from um.ac.ir M Haak, RE de Jong… – zabanshenasi.um.ac.ir … Affective dialogue systems : tutorial and research workshop, ADS ????, Kloster Irsee, Germany, June ??-??, ???? ; proceedings. … UML ???? : the unified modeling language : modeling languages and applications ; ?th international conference, Lisbon, Portugal, October ??-??, ???? … Related articles