Streaming Data & Dialog Systems


Streaming Data & Dialog Systems
Wikipedia: Data StreamsStreaming Data | Stream Processing


Cognitive dialog systems for dynamic environments: Progress and challenges F Putze… – Digital Signal Processing for In-Vehicle Systems and …, 2012 – Springer … This is done for multiple reasons. First, an adaptive dialog system needs online data streams from which it can … To that end, we installed multiple biosignal sensors in the car to get a reliable, continuous data stream without obstructing or distracting the user too much. … Cited by 2 – Related articles – All 2 versions

Highly Scalable Speech Processing on Data Stream Management System S Nishii… – Database Systems for Advanced Applications, 2012 – Springer … is a new computational paradigm for processing large amounts of streaming data in real … B., et al.: A Code Generation Approach to Optimizing High-Performance Distributed Data Stream Processing. … Y., et al.: A Study for a Scalability Evaluation Model of Spoken Dialogue System. …

BiosignalsStudio: a flexible framework for biosignal capturing and processing [PDF] from kit.edu D Heger, F Putze, C Amma, M Wand… – KI 2010: Advances in …, 2010 – Springer … base class can be easily plugged together to construct new data streams, thereby ensuring … 9]. The recognizer works in real-time and receives the data stream from the … In: Proceedings of the Affective Dialogue Systems Workshop, Kloster Irrsee, Germany (2004) [5] PROATECH … Cited by 7 – Related articles – All 4 versions

Speak4it and the Multimodal Semantic Interpretation System [PDF] from att.com M Johnston… – Twelfth Annual Conference of the …, 2011 – isca-speech.org … audio has become commonplace, Watson’s MSIS can handle complex HTTP data streams that comprise not … These data can be multiplexed into a single threaded data stream sent from a … B., House, D., and Wirén, M, “AdApt—A Multimodal Conversational Dialogue System in an … Related articles – All 5 versions

[PDF] Multimodal recognition of cognitive workload for multitasking in the car [PDF] from kit.edu F Putze, JP Jarvis… – Proceedings of the 20th …, 2010 – csl.anthropomatik.kit.edu … We have the goal to build a cognitive dialog system [7], ie a dialog system that has … driving situation will produce noisy signals, we mea- sure and combine multiple data streams to end … signals from the driver in the car to get a reliable, continuous data stream without obstructing … Cited by 5 – Related articles – View as HTML – All 8 versions

Dialog model development of a mobile information and reference robot V Budkov, M Prishchepa… – Pattern Recognition and Image …, 2011 – Springer … Processing incoming data streams from heterogeneous sensors, the control system produces commands to activate devices and applications, providing … Dialog system development is a complex task, and in dialogue framework development, first of all, expert knowledge of the … Related articles – All 7 versions

Multimodal analysis of body sensor network data streams for real-time healthcare MK Garg, DJ Kim, DS Turaga… – Proceedings of the …, 2010 – dl.acm.org … circuits, wireless communication, physiological sensor design, and multimedia stream processing, have led to … 3.1 System Design Solutions Streaming data ingest: There has been a significant … Dialogue Systems, Tutorial and Research Workshop, Kloster Irsee, Germany, June 14 … Cited by 4 – Related articles – All 2 versions

Supporting children’s social communication skills through interactive narratives with virtual characters [PDF] from lonklab.ac.uk ME Foster, K Avramides, S Bernardini… – Proceedings of the …, 2010 – dl.acm.org … A third type of high-level event represents a discrete state change drawn from a continuous data stream: for example, while the vision system continually publishes the users’ gaze coor- dinates at a high frame rate, the … Multimodal gen- eration in the COMIC dialogue system. … Cited by 4 – Related articles – All 6 versions

Multimodal local search in Speak4it [PDF] from ntu.edu.tw P Ehlen… – Proceedings of the 16th international conference …, 2011 – dl.acm.org … This multimodal data stream is received and de-multiplexed by a Multimodal Interaction Manager component. The user’s ink trace is passed to a gesture recognizer. Audio is … AdApt—A multimodal conversational dialogue system in an apartment domain. Proc. … Related articles – All 2 versions

Speak4IT: Multimodal interaction in the wild [PDF] from att.com M Johnston… – Spoken Language Technology …, 2010 – ieeexplore.ieee.org … This multimodal data stream is received and de-multiplexed by a Multimodal Interaction Manager component. … 2000. AdApt – A Multimodal Conversational Dialogue system in an Apartment Domain. In Proceedings of ICSLP 2000. Vol. 2, 134-137. … Related articles – All 2 versions

Collecting multimodal data in the wild M Johnston… – Proceedings of the 2012 ACM international …, 2012 – dl.acm.org … audio has become commonplace, Watson’s MSIS can handle complex HTTP data streams that comprise … These data can be multiplexed into a single threaded data stream sent from a … M., Whittaker, S., and Maloor, P, “MATCH: An Architecture for Multimodal Dialogue Systems. …

Thinking head: Towards human centred robotics DC Herath, C Kroos, CJ Stevens… – … Robotics & Vision ( …, 2010 – ieeexplore.ieee.org … is a critical focus — efficient processing of multiple high-volume data streams is a … from open agent-oriented systems previously used for multimodal dialogue systems (eg, [2 … is also provided for high frequency/high bandwidth applications such as those requiring streaming data. … Cited by 2 – Related articles

Speak4it: multimodal interaction for local search [PDF] from att.com P Ehlen… – … Conference on Multimodal Interfaces and the …, 2010 – dl.acm.org … This multimodal data stream is received and de-multiplexed by a Multimodal Interaction Manager component. … AdApt – A Multimodal Conversational Dialogue system in an Apartment Domain. In Proceedings of ICSLP 2000. Vol. 2, 134-137. … Related articles – All 2 versions

mTalk-A Multimodal Browser for Mobile Services [PDF] from att.com M Johnston, GD Fabbrizio… – Twelfth Annual Conference …, 2011 – isca-speech.org … in addition to the graph- ical user interface, an application needs to manage gestures, touches, and real-time data streams from and … Vasireddy, A. Stent, P. Ehlen, M. Walker, S. Whittaker, and P. Maloor, “MATCH: An archi- tecture for multimodal dialog systems,” in Proceedings … Cited by 1 – Related articles – All 7 versions

[PDF] Steps towards affordable android telepresence [PDF] from alex-tsamakos.com N Mavridis, A Tsamakos… – Proceedings of the …, 2011 – alex-tsamakos.com … For example, the current state of the art of dialogue systems for robots, is inadequate for dealing with broad, generic natural language interactions; also … The movement of the body of Person A will be captured by a Sensor System S in Room A, and this data stream, together with … Cited by 2 – Related articles – View as HTML – All 2 versions

[PDF] Explanations in dialogue systems through uncertain RDF knowledge bases [PDF] from mpg.de D Sonntag… – Workshop on Explanation-aware …, 2010 – domino.mpi-inf.mpg.de … This new backend can be integrated into a speech-based dialogue system to answer questions about a specific domain. … Automatically inferred knowledge by URDF provides a new data stream and explanations for future, artificial intelligence based interaction systems. … Cited by 2 – Related articles – View as HTML – All 8 versions

Adaptive systems for unsupervised speaker tracking and speech recognition T Herbig, F Gerl, W Minker… – Evolving Systems, 2011 – Springer … Typically, continuous data streams have to be handled without prior knowledge about the beginning and end of a speaker’s utterance, speaker … To retrieve all occurrences of one speaker in a data stream, an automatic speaker indexing known as agglom- erative clustering may … Cited by 1 – Related articles – All 2 versions

Emotion in Human-Computer Interaction C Peter… – Expanding the Frontiers of Visual Analytics and …, 2012 – Springer … Screen record- ing, gaze tracking, mouse and keyboard input are just basic components of data streams usually generated by nowadays usability programs. … cognitive load in the user to speed up the analysis process and to spot critical situations in the data stream more easily. …

Self-understanding and self-extension: A systems and representational approach [PDF] from bham.ac.uk JL Wyatt, A Aydemir, M Brenner… – Autonomous Mental …, 2010 – ieeexplore.ieee.org Page 1. 282 IEEE TRANSACTIONS ON AUTONOMOUS MENTAL DEVELOPMENT, VOL. 2, NO. 4, DECEMBER 2010 Self-Understanding and Self-Extension: A Systems and Representational Approach Jeremy L. Wyatt, Alper … Cited by 6 – Related articles – All 16 versions

Speech-based Non-prototypical Affect Recognition for Child-Robot Interaction in Reverberated Environments [PDF] from uni-erlangen.de M Wöllmer, F Weninger, S Steidl… – … Annual Conference of …, 2011 – isca-speech.org … modality and are increasingly employed for a vari- ety of applications including human-robot interaction, dialogue systems, voice command … phoneme estimates generated by a bidirec- tional Long Short-Term Memory recurrent neural network as two independent data streams. … Cited by 1 – Related articles – All 5 versions

Two-stream indexing for spoken web search [PDF] from www2011india.com J Ajmera, A Joshi, S Mukherjea, N Rajput… – Proceedings of the 20th …, 2011 – dl.acm.org … ABSTRACT This paper presents two-stream processing of audio to index the audio content for Spoken Web search. … The results suggest significant improvement over a meta-data-only or a speech-recognition- only system, thus justifying the two-stream processing ap- proach. … Cited by 2 – Related articles – All 7 versions

[PDF] The Automotive Ontology: Managing Knowledge Inside the Vehicle and Sharing it Between Cars [PDF] from auto-ui.org M Feld… – Proceedings of AutomotiveUI, 2011 – auto-ui.org … model. It contains discourse information on human-machine interaction, but also on inter-human in- teraction such as conversations. Dialog systems are heavily based on knowledge in this branch of the ontology. Knowing who … Cited by 1 – Related articles – View as HTML

Pervasive technologies and assistive environments: social impact, financial, government and privacy issues I Maglogiannis, F Makedon, G Pantziou… – Universal Access in the …, 2011 – Springer … in the Aged”, propose an integrated approach for activity monitoring by combining motion capture (action) and biosignals (physiological) parameters as synchronized data streams. … An initial implementation of a dialogue system realizing this cognitive model is also presented. … Cited by 1 – Related articles – All 4 versions

A generic framework for the inference of user states in human computer interaction S Scherer, M Glodek, G Layher, M Schels… – Journal on Multimodal …, 2012 – Springer … From the modeling view point it is crucial to design and use suitable features as well as classifiers: In order to fully access a modality, features need to be extracted from the corresponding data stream containing as much information about the target as possible; within the af …

Continuous F0 Modelling for HMM based Statistical Parametric Speech Synthesis [PDF] from cam.ac.uk K Yu… – Audio, Speech, and Language Processing, …, 2011 – ieeexplore.ieee.org … unvoiced regions as well as voiced regions. This provides a continuous F0 data stream which can be modelled by … using the same approach as in section III-B. Since the voicing condition is modelled by an independent data stream, there is no requirement for the statistical … Cited by 1 – Related articles – All 9 versions

Ego noise cancellation of a robot using missing feature masks G Ince, K Nakadai, T Rodemann, H Tsujino… – Applied Intelligence, 2011 – Springer Page 1. Appl Intell (2011) 34: 360–371 DOI 10.1007/s10489-011-0285-0 Ego noise cancellation of a robot using missing feature masks Gökhan Ince · Kazuhiro Nakadai · Tobias Rodemann · Hiroshi Tsujino · Jun-ichi Imura Published … Cited by 1 – Related articles – All 4 versions

Multi-stream LSTM-HMM decoding and histogram equalization for noise robust keyword spotting M Wöllmer, E Marchi, S Squartini… – Cognitive Neurodynamics, 2011 – Springer … We will focus on optimizing our keyword spotter for the SEMAINE system which was developed within the SEMAINE project.2 Unlike most task-oriented dialogue systems, the Sensitive Artificial Listeners representing the SEMAINE … and b1:T as two independent data streams. … Cited by 2 – Related articles – All 2 versions

Active Learning D Hakkani-Tür… – Spoken Language Understanding, 2011 – Wiley Online Library … To complement such data deluge, machine learning models that select salient data streams or patterns are crucial to improve the performance of the … the purpose of improving the expected error rate over time, hence adapting to the changes in the incoming data stream, in the … Related articles – All 2 versions

[PDF] AUDIO-VISUAL ISOLATED DIGIT RECOGNITION FOR WHISPERED SPEECH [PDF] from eurasip.org X Fan, C Busso… – 2011 – eurasip.org … stream training test Word Accuracy audio data neutral neutral 98.7% audio data whisper whisper 83.3% audio data neutral whisper … corpus collection is needed to demonstrate the effectiveness of the proposed algorithms in actual voiced communication/voice dialog systems. … Related articles – View as HTML – All 2 versions

A spatio-temporal approach to the discovery of online social trends [PDF] from uml.edu H Achrekar, Z Fang, Y Li, C Chen, B Liu… – Combinatorial …, 2011 – Springer … data collection engine would pro- duce a large volume of streaming data with spatio … Unfortunately, data is carried by a chaotic, noisy data stream and may be dis … Framework, Conversational Systems, Natural, Intelligent and Effective Interaction in Multimodal Dialogue Systems. … Related articles – All 3 versions

Frontiers, challenges, and opportunities for information retrieval: Report from SWIRL 2012 the second strategic workshop on information retrieval in Lorne [PDF] from elias-network.eu J Allan, B Croft, A Moffat… – ACM SIGIR Forum, 2012 – dl.acm.org Page 1. WORKSHOP REPORT Frontiers, Challenges, and Opportunities for Information Retrieval Report from SWIRL 2012 The Second Strategic Workshop on Information Retrieval in Lorne February 2012 Editors James Allan, Bruce Croft, Alistair Moffat, and Mark Sanderson …

[BOOK] Digital signal processing for in-vehicle systems and safety JHL Hansen, P Boyraz, K Takeda… – 2011 – books.google.com … Chapters 7 and 8 consider novel ways to start speech dialogs in cars, and cognitive dialog systems for dynamic environments respectively. … Chapter 21 considers multi- media streaming data over inter-vehicle communication networks. … Related articles – All 3 versions

Bidirectional LSTM networks for context-sensitive keyword detection in a cognitive virtual agent framework M Wöllmer, F Eyben, A Graves, B Schuller… – Cognitive Computation, 2010 – Springer … The aim of the SEMAINE project1 is to build a Sensitive Artificial Listener—a multimodal dialogue system with the social interaction skills needed for a sustained con … parent. The bold dashed lines in the BLSTM layer do not represent statistical relations but simple data streams. … Cited by 18 – Related articles – All 6 versions

Physiological Signals and Their Use in Augmenting Emotion Recognition for Human–Machine Interaction RB Knapp, J Kim… – Emotion-Oriented Systems, 2011 – Springer … The range of sampling rates is considerably reduced for wireless data acquisition systems. • Synchronization of multiple data streams: In many cases, more than one chan- nel of physiological data is analyzed simultaneously (or combined with video or audio streams). … Cited by 3 – Related articles – All 2 versions

Hybrid framework for improving collaborative capabilities in virtual organizations C Porumb, S Porumb, B Orza… – Automation Quality and …, 2010 – ieeexplore.ieee.org … The voice server receives the data streams and invokes the Automatic Speech Recognition component in order to get the system events. … [11] J. Van Kuppevelt, L. Dybkjaer, and NO Bernsen, Advances in Natural Multimodal Dialogue Systems, Springer Publishing House, 2005 Related articles – All 4 versions

Thinking Head Framework: An open architecture for human centred robotics DC Herath, Z Zhang… – Information and Automation …, 2010 – ieeexplore.ieee.org … based integration frameworks have been used as platforms for building dialogue systems for a number of years (eg, [3, 4]), such frameworks have not necessarily paid attention to handling real-time continuous processes or the demands of large volumes of streaming data. … Related articles

[PDF] A knowledge-based method for generating summaries of spatial movement in geographic areas [PDF] from upm.es M MOLINA… – International Journal On Artificial Intelligence …, 2010 – dia.fi.upm.es … spatial movement in geographical areas. The method can help humans to understand large data streams, such as the amounts of GPS data recorded by a variety of sensors in mobile phones, cars, etc. We describe the knowledge … Cited by 3 – Related articles – View as HTML – All 5 versions

Characterizing the effectiveness of tutorial dialogue with hidden Markov models [PDF] from ncsu.edu K Boyer, R Phillips, A Ingram, E Ha… – Intelligent Tutoring …, 2010 – Springer … direct applications in authoring data-driven tutorial dialogue system behavior and in research regarding the effectiveness of human tutors. … The entries in this problem-solving data stream were manually aggregated into significant student work events (Section 4.2), resulting in … Cited by 14 – Related articles – All 6 versions

Acoustic and Visual Cues of Turn-Taking Dynamics in Dyadic Interactions [PDF] from usc.edu B Xiao, V Rozgic, A Katsamanis… – … Annual Conference of …, 2011 – isca-speech.org … Bohus and Horvitz [10] designed a multi-party dialog system with three components: sensing conversational dynamics, real-time turn- taking decisions and … The data streams from the two lapel microphones and the two near view cameras were used for feature extraction. … Related articles – All 3 versions

Robust multi-stream keyword and non-linguistic vocalization detection for computationally intelligent virtual agents [PDF] from tu-muenchen.de M Wöllmer, E Marchi, S Squartini… – Advances in Neural …, 2011 – Springer … In contrast to most task-oriented dialogue systems, the Sensitive Artificial Lis- teners representing the SEMAINE system [9] focus on aspects of communication … a phoneme prediction according to Equa- tion 1 and the HMM models x1:T and b1:T as two independent data streams. … Cited by 3 – Related articles – All 5 versions

Maritime logistics and applications of information technologies KH Kim… – Computers and Industrial Engineering ( …, 2010 – ieeexplore.ieee.org … Figure 3. The structure of DiALog system [8]. … B. Edge Management Application EMA (Edge Management Application) is responsible for tag data collecting, filtering and grouping. Massive RFID, RTLS, Sensor tag data appears in form of data streams in EMA. … Related articles – All 4 versions

Simultaneous speech recognition and speaker identification T Herbig, F Gerl… – Spoken Language Technology …, 2010 – ieeexplore.ieee.org … in parallel to the standard codebook. However, the parallel computation significantly increases the computational load since the speech decoder has to process NSp +1 data streams in parallel. The Viterbi algorithm is more … Cited by 4 – Related articles

Social signal processing: The research agenda [PDF] from ic.ac.uk M Pantic, R Cowie, F D’Errico, D Heylen… – Visual Analysis of …, 2011 – Springer Page 1. Chapter 26 Social Signal Processing: The Research Agenda Maja Pantic, Roderick Cowie, Francesca D’Errico, Dirk Heylen, Marc Mehu, Catherine Pelachaud, Isabella Poggi, Marc Schroeder, and Alessandro Vinciarelli … Cited by 1 – Related articles – All 8 versions

WOZ acoustic data collection for interactive TV [PDF] from ua.es A Brutti, L Cristoforetti, W Kellermann… – Language Resources …, 2010 – Springer … A command-line program listens to the network card, connects to the array and stores the incoming data stream into a … Machine Interface (HMI) development which allows the user to design multimodal User Interfaces (UIs) with graphical, haptical, and speech dialog systems. … Cited by 8 – Related articles – All 21 versions

Comparison of technical filter mechanisms and defense mechanisms of the human mind F Gelbard, C Brandstatter, K Doblhammer… – AFRICON, …, 2011 – ieeexplore.ieee.org … Data streams from the internet are corrected if errors are detected and a certain amount of errors is not exceeded. … Simulating the emotion dynamics of a multimodal conversational agent, In Proceedings Tutorial and Research Workshop on Affective Dialogue Systems (ADS-04 … Related articles

[HTML] Interoperability and information brokers in public safety: an approach toward seamless emergency communications [HTML] from scielo.cl A Kuehn, M Kaschewsky, A Kappeler… – Journal of theoretical …, 2011 – SciELO Chile … that interacts with drivers in natural language, eg, for requesting data analysis over voice dialog systems). … for the detection of complex events (eg, interrelated events) in the data streams as well … can pinpoint problems much earlier than waiting for each single data stream to pass … Related articles – Cached – All 14 versions

Real-Time Meteorological Battlespace Characterization in Support of Sea Power 21 [PDF] from dtic.mil J Cook, M Frost, P Harasti, G Love, D Martinez… – 2011 – DTIC Document … 8 4.1.3 Unmanned Aerial Vehicle Observations UAV data have been integrated into the Nowcast system. Atmospheric observation data from the Predator UAV are contained in the data stream returned from the aircraft to the ground control station for aircraft control purposes. … Related articles – Library Search – All 4 versions

Mindreading as a Foundational Skill for Socially Intelligent Robots C Breazeal, J Gray… – Robotics Research, 2011 – Springer … Hence, modern approaches often apply probabilistic frameworks on perceptual data streams to learn and recognize plans (eg, [11, 8, 6]). Pollack … tor’s recipe-for-action [9]. This logical framework has been applied to symbolic domains such as collaborative dialog systems, but is … Cited by 1 – Related articles – All 2 versions

CoCITe-Coordinating Changes in Text [HTML] from computer.org J Wright… – Knowledge and Data Engineering, …, 2012 – ieeexplore.ieee.org … For some data streams, the regular Poisson and binomial distributions do not fit the data well because the dispersion is too high. … 2.1 Text Data Stream Consider a typical source of text data, structured into documents, each labeled with a time-stamp and optionally with metadata … Related articles – All 18 versions

Assessment of general applicability of ego noise estimation [PDF] from honda-ri.com G Ince, K Nakamura, F Asano… – … (ICRA), 2011 IEEE …, 2011 – ieeexplore.ieee.org … Except the system depicted in Fig. 2(a), no additional filtering is applied to the incoming data streams. To generate precise SNR conditions before mixing the noise recording and clean speech, we amplified speech signals based on their segmental SNR. … Cited by 2 – Related articles – All 3 versions

Towards Multimodal Driver’s Stress Detection [PDF] from universityoftexasatdallascomets.com H Boril, P Boyraz… – Digital Signal Processing for In-Vehicle …, 2012 – Springer … The emotional states in drivers were evoked during conversation with a dialog system. … The UTDrive corpus includes data from the above-mentioned sensor channels (13 separate data streams: two video, six audio, one GPS, one optical distance, one CAN-Bus, two pressure … Related articles – All 7 versions

[PDF] Speaker Verification On Summed-Channel Conditions With Confidence Measures [PDF] from 148.204.65.169 CV Avilés Casco, J Villalba López… – Computación y …, 2011 – 148.204.65.169 … In contrast to [Castaldo et al., 2008], we estimate the GMM using all available data in the recording, rather than processing 1 minute slices and applying a clustering technique. The later allows stream processing with 1 minute latency but the former yields better results. … Related articles – View as HTML – All 4 versions

[PDF] Social Signal Processing in Companion Systems-Challenges Ahead [PDF] from tu-berlin.de G Layher, S Tschechne, S Scherer… – Human-Computer …, 2012 – user.tu-berlin.de … possible configurations of objects and object parts a rich set of necessary features needs to be detected from input data streams. … re- search workshop on Perception and Interactive Technologies for Speech-Based Sys- tems: Perception in Multimodal Dialogue Systems, PIT ’08 … Related articles – View as HTML – All 3 versions

Multimodal fusion for multimedia analysis: a survey [PDF] from nus.edu.sg PK Atrey, MA Hossain, A El Saddik… – Multimedia Systems, 2010 – Springer … However, in general, these rules are domain specific and defining the rules requires proper knowledge of the domain. This fusion method is widely used in the domain of multimodal dialog systems and sports video analysis. 3.2 Classification-based fusion methods … Cited by 29 – Related articles – All 9 versions

Fusing eye gaze with speech recognition hypotheses to resolve exophoric references in situated dialogue [PDF] from aclweb.org Z Prasov… – Proceedings of the 2010 Conference on Empirical …, 2010 – dl.acm.org … from traditional telephony-based spoken dialogue systems and multimodal conversational interfaces, situated dialogue supports immersion and mobility in a visually rich … Figure 2: Sample parallel speech and eye gaze data streams, including a portion of the sample WCN … Cited by 4 – Related articles – All 11 versions

Design of the new prognosis wearable system-prototype for health monitoring of people at risk A Pantelopoulos… – Advances in Biomedical Sensing, …, 2010 – Springer … to derive an estimation of the patient’s overall health condition and iii) interacting with the patient in terms of an automated dialogue system in order to … The mobile phone is capable of analyzing the streaming data from the sensor in real-time and also transmitting them to a heart … Cited by 2 – Related articles – All 2 versions

Investigating the Relationship Between Dialogue Structure and Tutoring Effectiveness: A Hidden Markov Modeling Approach [PDF] from ncsu.edu KE Boyer, R Phillips, A Ingram, EY Ha… – International Journal of …, 2011 – IOS Press … This multiple regression approach is also widely used in natural language dialogue systems research outside of tutoring (Walker, Litman, Kamm, & … The entries in this problem-solving data stream were manually aggregated into significant student work events, resulting in 3,793 … Cited by 4 – Related articles – All 3 versions

Combining long short-term memory and dynamic bayesian networks for incremental emotion-sensitive artificial listening M Wollmer, B Schuller, F Eyben… – Selected Topics in …, 2010 – ieeexplore.ieee.org … SENSITIVE ARTIFICIAL LISTENING The aim of the SEMAINE project1 is to build a sensitive artificial listener—a multimodal dialogue system with the so- cial interaction skills … The bold dashed lines in the LSTM layer do not represent sta- tistical relations but simple data streams. … Cited by 37 – Related articles – All 4 versions

Bridging the gap between social animal and unsocial machine: A survey of social signal processing [PDF] from telecom-paristech.fr A Vinciarelli, M Pantic, D Heylen… – Affective Computing …, 2011 – ieeexplore.ieee.org Page 1. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING 1 Bridging the Gap Between Social Animal and Unsocial Machine: A Survey of Social Signal Processing Alessandro Vinciarelli, Maja Pantic, Dirk Heylen, Catherine … Cited by 5 – Related articles – All 11 versions

Tandem decoding of children’s speech for keyword detection in a child-robot interaction scenario [PDF] from kuleuven.be M Wöllmer, B Schuller, A Batliner… – ACM Transactions on …, 2011 – dl.acm.org … switching parent. They can change not only the set of parents but also the implementation (ie, the CPF) of a parent. The bold dashed lines in the BLSTM layer do not represent statistical relations but simple data streams. Assuming a … Cited by 1 – Related articles – All 3 versions

[BOOK] ECAI 2010: 19th European Conference on Artificial Intelligence Proccedings H Coelho – 2010 – books.google.com … 2010) Vol. 208. GL Pozzato, Conditional and Preferential Logics: Proof Methods and Theorem Proving Vol. 207. A. Bifet, Adaptive Stream Mining: Pattern Learning and Mining from Evolving Data Streams Vol. 206. T. Welzer …

Enhancing Performance through Pedagogy and Feedback: Domain Considerations for Intelligent Tutoring Systems BS Goldberg, HK Holden, KW Brawner… – The Interservice/Industry …, 2011 – NTSA … With new data streams being fed into the learner model, pedagogical decision functions can leverage this information to understand more about the current state of the … A concern with this approach is the accuracy of dialogue systems and their effect on training performance. … Related articles

Location grounding in multimodal local search [PDF] from att.com P Ehlen… – … Conference on Multimodal Interfaces and the …, 2010 – dl.acm.org … of recent movements of the map display and utterances spoken. This multimodal data stream is received and decoded by a Multimodal Interaction Manager component. The user’s ink trace is passed to a gesture recognition … Cited by 7 – Related articles – All 2 versions

[PDF] Random Indexing Re-Hashed [PDF] from velldal.net E Velldal – 2011 – velldal.net … Can easily add more data without recomputing R and G. ? Suitable for parallelization and stream processing. Erik Velldal Random Indexing Re-Hashed 7 / 15 Page 20. … Sahlgren, M. (2003). Content-based adaptivity in multilingual dialogue systems. … Related articles – View as HTML – All 4 versions

On-line emotion recognition in a 3-D activation-valence-time continuum using acoustic and linguistic cues [PDF] from utwente.nl F Eyben, M Wöllmer, A Graves, B Schuller… – Journal on Multimodal …, 2010 – Springer … 9 Fig. 1 Architecture of the SEMAINE system 3 The SEMAINE system architecture The aim of the SEMAINE project1 is to build a Sensitive Artificial Listener—a multimodal dialogue system with the social interaction skills needed for a sustained conversation with a human user. … Cited by 16 – Related articles – All 3 versions

[BOOK] Operational Risk Management: a practical approach to intelligent data analysis [PDF] from kpa.co.il RS Kenett, Y Raanan – 2011 – books.google.com Page 1. Editors RON KENETT YOSSI RAANAN Operational Risk Management A practical approach to intelligent data analysis Page 2. Red box rules are for proof stage only. Delete before final printing. Operational Risk Management … Cited by 11 – Related articles – Library Search – All 4 versions

[PDF] Report on State of the Art, Current Possibilities and Options [PDF] from idiap.ch A Popescu-Belis – 2011 – idiap.ch … Useful studies here are those dealing with mixed-initiative computer systems (although our target is not a full-fledged dialogue system). … Coden, AR and Brown, EW (2006). Automatic search from streaming data. Information Retrieval, 9:95–109. … Related articles – View as HTML

International Large-Scale Vehicle Corpora for Research on Driver Behavior on the Road K Takeda, JHL Hansen, P Boyraz… – Intelligent …, 2011 – ieeexplore.ieee.org … How to integrate the data streams associated with driving is one of the central issues in advanced vehicle tech- nologies. Therefore, the lack of common research resources including in-vehicle data is a crucial issue in the research com- munity. … Related articles – All 3 versions

Gaze, conversational agents and face-to-face communication [PDF] from archives-ouvertes.fr G Bailly, S Raidt… – Speech Communication, 2010 – Elsevier Cited by 15 – Related articles – All 11 versions

[PDF] Research, Teaching, and Community for the New Decade [PDF] from 130.49.220.23 H Varotto – LINKS, 2010 – 130.49.220.23 … NSF Hauskrecht Detecting Deviations in Clinical Care in ICU Data Streams NIH Hauskrecht Discovering Complex Anomalous Patterns NIH … NSF Litman An Affect-Adaptive Spoken Dialogue System that Responds Based on User Model and Multiple Affect States NSF … Related articles – View as HTML – All 12 versions

Self-learning speaker identification for enhanced speech recognition T Herbig, F Gerl… – Computer Speech & Language, 2011 – Elsevier Related articles – All 2 versions

Low cost remote gaze gesture recognition in real time D Rozado, FB Rodriguez… – Applied Soft Computing, 2012 – Elsevier … not very extensive. Authors in [11] used gaze gestures in a dialog system to facilitate communication but the subjects involved in the experiment were not trying to consciously perform gaze gestures. Research has been done …

Unsupervised Speech Controlled System with Long-Term Adaptation T Herbig, F Gerl… – Self-Learning Speaker Identification, 2011 – Springer … This approach allows accurate speech modeling for each speaker. However, the parallel computation significantly increases the computational load since the speech decoder has to process NSp + 1 data streams in paral- lel. …

LSTM-Modeling of continuous emotions in an audiovisual affect recognition framework M Wöllmer, M Kaiser, F Eyben… – Image and Vision Computing, 2012 – Elsevier … as more natural and more enjoyable to use [1]. Examples for successful applications of socially competent human-computer interaction via automatic emotion recognition can be found in the areas of human-robot communication, call center dialog systems, computer games, and …

The German TR 440 Computer: Software and Its Development HJ Siegert – Annals of the History of Computing, IEEE, 2010 – ieeexplore.ieee.org … experimental implementations of parts. This meant that potential customers, even at universities, had no experience with dialog systems nor were they familiar with the technical concepts and notations. An example: Staff members … Cited by 5 – Related articles – All 12 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 … of transition among hidden states. Therefore, this model is more effectively used to model and segment a continuous observed real data stream (eg, speaker diarization and speech recognition). If the segmentation process, outputting … Related articles – All 2 versions

Fundamentals of agent perception and attention modelling [PDF] from coventry.ac.uk C Peters, G Castellano, M Rehm, E André… – Emotion-Oriented …, 2011 – Springer … characteristics of movement. EyesWeb XMI2 is an open software platform for the synchronised analysis of multimodal data streams which supports real-time analysis of body movement expressivity (Camurri et al., 2007). It consists … Cited by 1 – Related articles – All 9 versions

[BOOK] Modern Approaches in Applied Intelligence: 24th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, … KG Mehrotra, CK Mohan, JC Oh, PK Varshney… – 2011 – books.google.com … 579 Page 16. Table of Contents – Part I Section 1: Incremental Clustering and Novelty Detection Techniques and Their Application to Intelligent Analysis of Time Varying Information Classification Model for Data Streams Based on Similarity ….. … Related articles – Library Search – All 4 versions

The expanding horizons of corpus analysis [PDF] from cmu.edu B MacWhinney – Language and Computers, 2011 – ingentaconnect.com Page 1. The expanding horizons of corpus analysis Brian MacWhinney Carnegie Mellon University Abstract By including a focus on multimedia interactions linked to transcripts, corpus linguistics can vastly expand its horizons. … Related articles – All 2 versions

[HTML] A Call Control and Multi-Party Usage Framework for the Session Initiation Protocol (SIP) [HTML] from ietf.org J Rosenberg, R Mahy, D Petrie, A Johnston… – 2010 – rsync.tools.ietf.org … is obviously active.) Some robotic participants (such as a voice-messaging system, an instant-messaging agent, or a voice- dialog system) may be active … A session is defined as “a set of multimedia senders and receivers and the data streams flowing from senders to receivers”. … Cached – All 23 versions

Accessibility and Design for All Solutions Through Speech Technology D Freitas – Speech Technology, 2010 – Springer … the problem is to use speech through a combined wireless micro- phone/earphone associated with a special dialogue system prepared to … to the use of special modelling techniques [6] like parallel model combination, auditory modelling, multi-band and multi-stream processing. … Related articles – All 2 versions

Implementation of traceability using a distributed RFID-based mechanism JP Muñoz-Gea, J Malgosa-Sanahuja… – Computers in …, 2010 – Elsevier … In the DIALOG system every product is implemented as a software agent [18], and the information of each of them is accessed and updated … In addition, the ALE standard also supports the declaration of logical readers that collect the data streams from multiple physical readers. … Cited by 2 – Related articles – All 5 versions

Enabling through life product-instance management: Solutions and challenges DC Ranasinghe, M Harrison, K Främling… – Journal of Network and …, 2011 – Elsevier … 3. 2.2.2. DIALOG system (Helsinki University of Technology). The DIALOG system (DIALOG, 2009) is an open-source solution for tracking objects and accessing data about the objects (Kärkkäinen et al., 2003) using the DIALOG middleware system as illustrated in Fig. … Cited by 3 – Related articles – All 5 versions

[HTML] Emotion on the Road&# 8212; Necessity, Acceptance, and Feasibility of Affective Computing in the Car [HTML] from hindawi.com F Eyben, T Poitschke, C Blaschke… – Advances in Human- …, 2010 – hindawi.com … Thereby emotion serves as contextual knowledge that indicates how the dialogue system has to interpret the output of the automatic speech recogniser (eg, the use of irony may depend on the user’s emotional state, also there seems to be a reduced vocabulary in highly … Cited by 7 – Related articles – Cached – All 10 versions

Computers in the human interaction loop [PDF] from gmu.edu A Waibel, R Stiefelhagen, R Carlson… – Handbook of Ambient …, 2010 – Springer … different user interface conventions. Standardization and better graphical user interfaces, multimodal human-machine dialog systems including speech, pointing, mousing have all contributed to improve this situation. Yet, they have … Cited by 16 – Related articles – All 8 versions

Mining Creativity Research to Inform Design Rationale in Open Source Communities [PDF] from jyu.fi W Burleson… – 2011 – jyx.jyu.fi … 1979) participatory approach to the development of the issue-based information system (IBIS) and its use as a tool for design rationale have advanced approaches to shared dialogue; recent work on computational support and analysis of shared dialogue systems have further … Cited by 1 – Related articles – All 3 versions

Developing serious games for cultural heritage: a state-of-the-art review EF Anderson, L McLoughlin, F Liarokapis, C Peters… – Virtual reality, 2010 – Springer … These technologies include: – the Quest3D visualisation engine (Godbersen 2008) – Instinct(maker) artificial life engine (Toulouse Univer- sity) (Sanchez et al. 2004) – ATOM Spoken Dialogue System (http://www.agilingua. … Cited by 3 – Related articles – All 6 versions

[BOOK] Dialect Accent Features for Establishing Speaker Identity: A Case Study M Kulshreshtha, R Mathur – 2012 – 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 …

Multi-modal learning D Sko?caj, M Kristan, A Vrecko… – Cognitive …, 2010 – books.google.com Page 273. 7 Multi-modal Learning Danijel Sko?caj1, Matej Kristan1, Alen Vre?cko1, Ale?s Leonardis1, Mario Fritz2, Michael Stark2, Bernt Schiele2, Somboon Hongeng3, and Jeremy L. Wyatt3 1 VICOS Lab, University of Ljubljana, Ljubljana, Slovenia first. last@ fri. uni-lj. … Cited by 1 – Related articles

Implementation and Performance Exploration of a Cross-Genre Part of Speech Tagging Methodology to Determine Dialog Act Tags in the Chat Domain [PDF] from dtic.mil JR Hitt – 2010 – DTIC Document … Due to IRC’s synchronous nature, users may provide their inputs at any time. There is no requirement for turn-taking as commonly found in spoken dialog. Hence, IRC data streams frequently consist of multiple, interleaved conversations further complicating analysis. For … Cited by 1 – Related articles – Library Search – All 5 versions

Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge [PDF] from kuleuven.be B Schuller, A Batliner, S Steidl… – Speech Communication, 2011 – Elsevier Cited by 36 – Related articles – All 9 versions

Convivial Ambient Technologies: Requirements, Ontology and Design [PDF] from uni.lu P Caire… – The Computer Journal, 2010 – Br Computer Soc … concurrent programs. As such, coordination focuses on patterns that specifically deal with interaction. It has mainly been applied for coordinating data streams, but it can also be used for other coordination tasks. 2.4. Summary Socio … Cited by 3 – Related articles – All 6 versions

[BOOK] Virtual and Mixed Reality-New Trends: International Conference, Virtual and Mixed Reality 2011, Held as Part of HCI International 2011, Orlando, FL, USA, … R Shumaker – 2011 – books.google.com Page 1. Randall Shumaker (Ed.) Virtual and Mixed Reality New Trends International Conference, Virtual and Mixed Reality 2011 Held as Part of HCI International 2011 Orlando, FL, USA, July 2011, Proceedings, Part I 3artl HCI2011 INTERNATIONAL ¦0 Springer Page 2. … Related articles – Library Search

[BOOK] Affective Computing and Intelligent Interaction: Fourth International Conference, ACII 2011, Memphis, TN, USA, October 9-12, 2011, Proceedings A Graesser, B Schuller… – 2011 – books.google.com Page 1. LNCS 6974 Sidney D’Me]10 Arthur Graesser Bjiirn Schuller lean-Claude Martin (Eds.) Affective Computing and Intelligent Interaction 4th International Conference, ACII 2011 Memphis, TN, USA, October Z011 Proceedings, Part I Q Spnnger Page 2. … Related articles

Fusion multimodale et services Web [PDF] from etsmtl.ca A Zaguia – 2010 – espace.etsmtl.ca Page 1. ECOLE DE TECHNOLOGIE SUPERIEURE UNIVERSITÉ DU QUÉBEC MEMOIRE PRESENTE A L’ÉCOLE DE TECHNOLOGIE SUPÉRIEURE COMME EXIGENCE PARTIELLE À L’OBTENTION DE LA MAÎTRISE EN GÉNIE DE LA PRODUCTION AUTOMATISÉE M. Ing. …

[BOOK] Speech in Mobile and Pervasive Environments N Rajput… – 2012 – books.google.com … call-flow characterization 6.7.7 SAMVAAD: Architecture, implementation and experiments 6.7.8 Splitting dialog call-flows 6.8 Conclusion 6.9 Summary and future work Bibliography Architecture of Mobile Speech-Based and Multimodal Dialog Systems 7.1 Introduction 7.2 … Related articles

[PDF] Multi-Modal Scene Understanding for Robotic Grasping [PDF] from kth.se J BOHG – 2011 – csc.kth.se … We consider multiple modalities including monocular and stereo vision, haptic sensing and information obtained through a human-robot dialog system. … 67 5.1 System Overview . . . . . 68 5.2 Dialog System . . . . . … Related articles – View as HTML – All 2 versions

[PDF] SPECIAL ISSUE ON CREATIVITY AND RATIONALE IN SOFTWARE DESIGN, Part 2 [PDF] from jyu.fi M Kankaanranta – 2011 – humantechnology.jyu.fi Page 1. Volume 1, Number 2, October 2005 Marja Kankaanranta, Editor ISSN: 1795-6889 Volume 7, Number 2, August 2011 SPECIAL ISSUE ON CREATIVITY AND RATIONALE IN SOFTWARE DESIGN, Part 2 John M. Carroll, Guest Editor Pertti Saariluoma, Editor in Chief … Related articles – View as HTML – All 2 versions

RFID enabled traceability networks: a survey [PDF] from adelaide.edu.au Y Wu, DC Ranasinghe, QZ Sheng… – Distributed and Parallel …, 2011 – Springer Page 1. Distrib Parallel Databases DOI 10.1007/s10619-011-7084-9 RFID enabled traceability networks: a survey Yanbo Wu · Damith C. Ranasinghe · Quan Z. Sheng · Sherali Zeadally · Jian Yu © Springer Science+Business Media, LLC 2011 … Cited by 3 – Related articles – All 7 versions