570 Hits in 4.5 sec

Asgard: A portable architecture for multilingual dialogue systems

Jingjing Liu, Panupong Pasupat, Scott Cyphers, Jim Glass
2013 2013 IEEE International Conference on Acoustics, Speech and Signal Processing  
Spoken dialogue systems have been studied for years, yet portability is still one of the biggest challenges in terms of language extensibility, domain scalability, and platform compatibility.  ...  , which supports expert-free development of multilingual dialogue systems and seamless deployment to mobile platforms.  ...  INTRODUCTION Spoken dialogue systems (SDS) have been studied for many decades.  ... 
doi:10.1109/icassp.2013.6639301 dblp:conf/icassp/LiuPCG13 fatcat:ccl3fmipsjdmba3tu4nglme6em

Commercialization of natural language processing technology

Deborah A. Dahl, Lewis M. Norton, K. W. Scholz
2000 Communications of the ACM  
The initial architecture of a text processing system was in place by 1986 [10] and was extended to process spoken language in 1989 [4].  ...  Successful commercial deployment of natural language understanding (NLU) products requires far more than accurate technology.  ...  The Unisys Natural Language Assistant represents a significant step toward widespread and practical natural language understanding capabilities for systems ranging from speech therapy to mortgage quotations  ... 
doi:10.1145/352515.352525 fatcat:dcld4d42tzcctjfuget6wrmutu

A collective data generation method for speech language models

Sean Liu, Stephanie Seneff, James Glass
2010 2010 IEEE Spoken Language Technology Workshop  
Our results show that AMT text queries are effective for initial language model training for spoken dialogue systems, and that crowdsourced speech collection within the context of a spoken dialogue framework  ...  Recently we began using Amazon Mechanical Turk (AMT), an Internet marketplace, to deploy our spoken dialogue systems to large audiences for user testing and data collection purposes.  ...  INTRODUCTION Language models for speech recognizers require a substantial amount of data. Amassing quality data for spoken dialogue systems, however, is traditionally a laborious task.  ... 
doi:10.1109/slt.2010.5700855 dblp:conf/slt/LiuSG10 fatcat:t3xrawujinfetg2oobam2pcd4q

Automating spoken dialogue management design using machine learning: An industry perspective

Tim Paek, Roberto Pieraccini
2008 Speech Communication  
In designing a spoken dialogue system, developers need to specify the actions a system should take in response to user speech input and the state of the environment based on observed or inferred events  ...  Researchers have recently pursued methods for automating the design of spoken dialogue management using machine learning techniques such as reinforcement learning.  ...  Commercial development and deployment The development of a commercial spoken dialogue system (SDS) is a complex process. Dialogue management is only a part of it, though arguably the most expensive.  ... 
doi:10.1016/j.specom.2008.03.010 fatcat:ifno5nvyg5cdhkrlxkidejcqg4

An Architecture to Develop Multimodal Educative Applications with Chatbots

David Griol, Zoraida Callejas
2013 International Journal of Advanced Robotic Systems  
Our proposal provides a modular and scalable framework to develop such systems efficiently.  ...  However, in order for them to be widely employed and accepted as a learning resource, they must be easy to use and friendly.  ...  Similarly, ITSPOKE [21] is a spoken dialogue tutoring system that engages the students in a spoken dialogue to provide feedback and correct misconceptions for tutoring conceptual physics.  ... 
doi:10.5772/55791 fatcat:zz7sgpdasbd5dg7icv47yfz454

Tactical Language and Culture Training Systems: Using AI to Teach Foreign Languages and Cultures

W. Lewis Johnson, Andre Valente
2009 The AI Magazine  
This paper describes the architecture of TLCTS and the artificial intelligence technologies that it employs, and presents results from multiple evaluation studies that demonstrate the benefits of learning  ...  The Tactical Language and Culture Training System (TLCTS) helps people quickly acquire communicative skills in foreign languages and cultures.  ...  Modeling Dialogue One key challenge for the dialogues in TLCTS is to manage the variability of the spoken inputs a learner may produce.  ... 
doi:10.1609/aimag.v30i2.2240 fatcat:rog4z2bspnazzozqguule3gmfy

Open and extendable speech recognition application architecture for mobile environments

Tanel Alumäe, Kaarel Kaljurand
2012 Workshop on Spoken Language Technologies for Under-resourced Languages  
The system consists of a speech recognition server and a client for the Android mobile operating system.  ...  This paper describes a cloud-based speech recognition architecture primarily intended for mobile environments.  ...  In addition to usability, we had a number of aspects in mind when designing the architecture of the system: • Scalability: it must be easy to scale the system to a large number of concurrent users. • Language  ... 
dblp:conf/sltu/AlumaeK12 fatcat:ol3aw2grfrcofk3ozsriicyrue

Slugbot: An Application of a Novel and Scalable Open Domain Socialbot Framework [article]

Kevin K. Bowden, Jiaqi Wu, Shereen Oraby, Amita Misra, Marilyn Walker
2018 arXiv   pre-print
We describe our semistructured, scalable framework for crafting topic-specific dialogue flows, and give details on our dialogue management schemes and scoring mechanisms.  ...  In this paper we introduce a novel, open domain socialbot for the Amazon Alexa Prize competition, aimed at carrying on friendly conversations with users on a variety of topics.  ...  Figure 3 depicts the architecture of our web server in details.  ... 
arXiv:1801.01531v1 fatcat:xiiltshtvjbyfnznaspj5hkftu

Voice2Web: Architecture for Managing Voice-Application Access to Web Resources [chapter]

Jan Rudinsky, Tomas Mikula, Lukas Kencl, Jakub Dolezal, Xavier Garcia
2009 Lecture Notes in Computer Science  
We present Voice2Web, an architecture allowing to manage access to the resources of the World Wide Web using voice interaction.  ...  Advances in voice-recognition platforms have led to new possibilities in deploying automated voice-interactive engines for Web content.  ...  We also thank CESNET for the generous lending of project equipment and Vodafone Foundation Czech Republic for the kind student scholarship support.  ... 
doi:10.1007/978-3-642-04994-1_10 fatcat:av3tlv6yevd37gaslx7ji26czm

Perceptive animated interfaces: first steps toward a new paradigm for human-computer interaction

R. Cole, S. Van Vuuren, B. Pellom, K. Hacioglu, Jiyong Ma, J. Movellan, S. Schwartz, D. Wade-Stein, W. Ward, Jie Yan
2003 Proceedings of the IEEE  
We then show how existing dialogue system architectures can be transformed into perceptive animated interfaces by integrating computer vision and animation capabilities.  ...  We conclude by describing the Colorado Literacy Tutor, a computer-based literacy program that provides an ideal testbed for research and development of perceptive animated interfaces, and consider next  ...  We describe a set of research tools that provide a foundation for transforming spoken dialogue systems into perceptive animated interfaces.  ... 
doi:10.1109/jproc.2003.817143 fatcat:awqjxnxwkbefzcoewu7bhy7ie4

IVR Junction: Building Scalable and Distributed Voice Forums in the Developing World

Aditya Vashistha, William Thies
2012 USENIX/ACM Workshop on Networked Systems for Developing Regions  
We also present a new open-source system, IVR Junction, that leverages existing free services and commercial tools to simplify the process of creating a voice forum.  ...  IVR Junction utilizes familiar cloud-based services to provide free content hosting and moderation, as well as a novel mechanism for automatically synchronizing content across geographically-dispersed  ...  Acknowledgments We are grateful to Arjun Venkatraman, Shubhranshu Choudhary, and Ed Cutrell, as well as the anonymous reviewers, for helpful comments and feedback.  ... 
dblp:conf/nsdr/VashisthaT12 fatcat:cvhffqslifafhckeh7sbjpf4xy

Extending Distributed GIS to Support Geo-Collaborative Crisis Management

Guoray Cai
2005 Annals of GIS  
An implementation of an intelligent, multimodal, multi-user geographic information environment, called GCCM_Connect, is presented as a proof-of-concept for the proposed architecture.  ...  Crises are often complex, geographical scale problems that require professionals to work in teams while dealing with a large amount of geographic information for decision making.  ...  ACKNOWLEDGMENTS This research is supported by a grant from NSF (NSF-EIA-0306845).  ... 
doi:10.1080/10824000509480595 fatcat:5vr2l667gvc3nclgtewg5dnllm

Evaluation of a hierarchical reinforcement learning spoken dialogue system

Heriberto Cuayáhuitl, Steve Renals, Oliver Lemon, Hiroshi Shimodaira
2010 Computer Speech and Language  
a reasonable hand-coded strategy; and (c) hierarchical reinforcement learning dialogue agents are feasible and promising for the (semi) automatic design of optimized dialogue behaviours in larger-scale  ...  We describe an evaluation of spoken dialogue strategies designed using hierarchical reinforcement learning agents.  ...  or out-of-vocabulary words), it was not possible to extract a user dialogue act contributing to the conversation (Table 19) .  ... 
doi:10.1016/j.csl.2009.07.001 fatcat:hrjxs2dv3ja4jioj4p56mz6h6q

IAServ: An Intelligent Home Care Web Services Platform in a Cloud for Aging-in-Place

Chuan-Jun Su, Chang-Yu Chiang
2013 International Journal of Environmental Research and Public Health  
Architecturally the implemented IAServ leverages web services and cloud computing to provide economic, scalable, and robust healthcare services over the Internet.  ...  This paper presents the development and overall architecture of IAServ (the Intelligent Aging-in-place Home care Web Services Platform) to provide personalized healthcare service ubiquitously in a cloud  ...  The proposed system design can serve as the foundation for an economic, scalable, and robust Web-based healthcare platform.  ... 
doi:10.3390/ijerph10116106 pmid:24225647 pmcid:PMC3863890 fatcat:jv73l7t5qfhdvlumrohvesfqmy

Systems Engineering and Conversational Agents [chapter]

James O'Shea, Zuhair Bandar, Keeley Crockett
2011 Intelligent Systems Reference Library  
a number of directions for systems engineers who wish to participate in CA research.  ...  A CA is a computer program which interacts with a user through natural language dialogue and provides some form of service.  ...  Dialogue Systems Spoken Dialogue Systems (SDSs) are concerned with the conversion of speech into text.  ... 
doi:10.1007/978-3-642-17931-0_8 fatcat:i5lq6nx2znbuhi55x6pt7rxyqa
« Previous Showing results 1 — 15 out of 570 results