Artificial Retrieval of Information Assistants - Virtual Agents with Linguistic Understanding, Social skills, and Personalised Aspects | ARIA-VALUSPA | Project | Results | H2020 | CORDIS

Livrables

Implementation of multi-lingual task-based dialogue system for the chosen scenario

Implementation of multilingual taskbased dialogue system for the chosen scenario

Multi-lingual realisation of Book-ARIA using M2 system

Multilingual realisation of BookARIA using milestone 2 system

Implementation of adaptive task-based dialogue system

Implementation of adaptive taskbased dialogue system

Implementation of cross-domain, context-sensitive speech analysis

Implementation of crossdomain contextsensitive speech analysis

First integrated system with simple support for web and mobile device user interfaces

The first integrated system with simple support for web and mobile device user interfaces

Release of the multilingual, adaptive dialogue toolbox

Release of the multilingual adaptive dialogue toolbox

Implementation of long-term adaptation for speech analysis

Implementation of longterm adaptation for speech analysis

Implementation of adaptive audiovisual communicative behaviour generation
Uni-lingual realisation of Book-ARIA using M1 system

Unilingual realisation of BookARIA using the system delivered at Milestone 1

Implementation of overall dynamic audiovisual communicative behaviour generation
Fine-tuned, multi-lingual realisation of Book-ARIA using M3 system

Finetuned multilingual realisation of BookARIA using M3 system

Second integrated system with improved real-time capabilities in distributed environments

Second integrated system with improved realtime capabilities in distributed environments

Final adaptive audiovisual communicative behaviour generation
Final integrated system with documented support for web standard technologies
Implementation of multi-lingual user- and environment-adaptive speech analysis

Implementation of multilingual user and environmentadaptive speech analysis

Ethical Policies

Report on applied ethical practices including informed consent forms ethical approval for experiments and data collection and certifications of compliance with national and EU legislation

Final report on standardisation and workshops activities
Evaluation report
Data Management Plan

The Data Management Plan will describe the data management life cycle for the Wizard of Oz and fully automatic ARIA generated data sets It will outline how our collected research data will be handled during and after ARIAVALUSPA It will describe what data will be collected processed or generated and following what methodology and standards whether and how this data will be shared andor made open and how it will be curated and preservedWe are committed to making all our data fully available to the research community through easily accessible web interfaces similar to the SEMAINE database A minor part of the data may be temporarily withheld from the public to allow the team to organise challenges for the research community on unseen data

Public access to interactive ARIA-VALUSPA platform under a research license
Project website, first version

Project website first version

Public access to interactive system data
Public access to labelled Wizard-of-Oz data

Public access to labelled WizardofOz data

Publications

Cascaded continuous regression for real-time incremental face tracking

Auteurs: E. Sánchez-Lozano, B. Martinez, G. Tzimiropoulos, M.F. Valstar
Publié dans: ECCV, 2016
Éditeur: IEEE

Topic switch models for dialogue management in virtual humans

Auteurs: W. Zhu, A. Chowanda, M.F. Valstar
Publié dans: IVA, 2016
Éditeur: Springer

Deep canonical time warping

Auteurs: George Trigeorgis, Mihalis A. Nicolaou, Stefanos Zafeiriou, Björn Schuller
Publié dans: CVPR, 2016
Éditeur: IEEE

Facing realism in spontaneous emotion recognition from speech: feature enhancement by autoencoder with LSTM neural networks

Auteurs: Zixing Zhang, Fabien Ringeval, Jing Han, Jun Deng, Erik Marchi, Björn Schuller
Publié dans: Interspeech, 2016
Éditeur: ISCA

Classifying emotion-antecedent appraisal in brain activity using machine learning methods

Auteurs: Kornelia Gentsch, Eduardo Coutinho, Florian Eyben, Björn Schuller, Klaus R. Scherer
Publié dans: 2015
Éditeur: ISRE

Dynamic active learning based on agreement, applied to emotion recognition in spoken interactions

Auteurs: Yue Zhang, Eduardo Coutinho, Zixing Zhang, Caijiao Quan, Björn Schuller
Publié dans: ICMI, 2016
Éditeur: ACM

AV+EC 2015 –- The first affect recognition Challenge bridging across audio, video, and physiological Data

Auteurs: Fabien Ringeval, Björn Schuller, Michel Valstar, Shashank Jaiswal, Erik Marchi, Denis Lalanne, Roddy Cowie, Maja Pantic
Publié dans: MM, 2015
Éditeur: ACM

Agreement-based dynamic active learning with least, medium certainty query strategies

Auteurs: Yue Zhang, Eduardo Coutinho, Zixing Zhang, Caijiao Quan, Björn Schuller
Publié dans: Advances in Active Learning : Bridging Theory, Practice Workshop, 2015
Éditeur: IMLS

Cross Modal Evaluation of High Quality Emotional Speech Synthesis with the Virtual Human Toolkit

Auteurs: B. Potard, M. Aylett, D. Braude.
Publié dans: IVA, 2016
Éditeur: Springer

Sincerity, deception in speech: Two sides of the same coin? A transfer- and multi-task learning perspective

Auteurs: Yue Zhang, Felix Weninger, Zhao Ren, Björn Schuller
Publié dans: ICMI, 2016
Éditeur: ACM

Computational Models of Emotion, Personality, and Social Relationships for Interactions in Games

Auteurs: A. Chowanda, P. Blanchfield, M. Flintham and M.F. Valstar
Publié dans: AAMAS, 2016
Éditeur: IFAAMAS

Combining Hierarchical Classification with Frequency Weighting for the Recognition of Eating Conditions

Auteurs: Johannes Wagner, Andreas Seiderer, Florian Lingenfelser, Elisabeth André
Publié dans: Interspeech, 2015
Éditeur: ISCA

Building autonomous sensitive artificial listeners (extended abstract)

Auteurs: Marc Schröder, Elisabetta Bevacqua, Roddy Cowie, Florian Eyben, Hatice Gunes, Dirk Heylen, Mark ter Maat, Gary McKeown, Sathish Pammi, Maja Pantic, Catherine Pelachaud, Björn Schuller, Etienne de Sevin, Michel Valstar, Martin Wöllmer
Publié dans: ACII, 2015
Éditeur: IEEE

TRIC-track: Tracking by Regression with Incrementally Learned Cascades

Auteurs: X. Wang, M.F. Valstar, B. Martinez, M.H. Khan, T.P. Pridmore
Publié dans: ICCV, 2015
Éditeur: IEEE

AV+ EC 2015--The First Affect Recognition Challenge Bridging Across Audio, Video, and Physiological Data

Auteurs: Ringeval, F., Schuller, B., Valstar, M., Jaiswal, S., Marchi, E., Lalanne, D., Cowie, R. and Pantic, M
Publié dans: AVEC, 2015
Éditeur: ACM

Improving social relationships in face-to-face human-agent interactions: when the agent wants to know user’s likes and dislikes

Auteurs: Caroline Langlet, Chloe Clavel
Publié dans: ACL, 2015
Éditeur: Association for Computational Linguistics and The Asian Federation of Natural Language Processing

Don't Say Yes, Say Yes: Interacting with Synthetic Speech Using Tonetable

Auteurs: M. Aylett, B. Potard, G. Pullin, S. Hennig, D. Braude, M. Antunes Ferreira
Publié dans: CHI EA '16, 2016
Éditeur: ACM

On rater reliability, correlation based dynamic active learning

Auteurs: Yue Zhang, Eduardo Coutinho, Zixing Zhang, Michael Adam, Björn Schuller
Publié dans: ACII, 2015
Éditeur: AAAC

Bird sounds classification by large scale acoustic features, extreme learning machine

Auteurs: Kun Qian, Zixing Zhang, Fabien Ringeval, Björn Schuller
Publié dans: GlobalSIP, 2015
Éditeur: IEEE

Face reading from speech –- predicting facial action units from audio cues

Auteurs: Fabien Ringeval, Erik Marchi, Marc Mehu, Klaus Scherer, Björn Schuller
Publié dans: Interspeech, 2015
Éditeur: ISCA

The Effects of Interrupting Behavior on Interpersonal Attitude and Engagement in Dyadic Interactions

Auteurs: Angelo Cafaro, Nadine Glas, Catherine Pelachaud
Publié dans: AAMAS, 2016
Éditeur: Springer

Exploring the importance of individual differences to the automatic estimation of emotions induced by music

Auteurs: Hesam Sagha, Eduardo Coutinho, Björn Schuller
Publié dans: MM, 2015
Éditeur: ACM

Learning to transfer: transferring latent task structures and its application to person-specific facial action unit detection

Auteurs: T. Almaev, B. Martinez and M.F. Valstar
Publié dans: ICCV, 2015
Éditeur: IEEE

Adapting sentiment analysis to face-to-face human-agent interactions: from detection to evaluation issues

Auteurs: Caroline Langlet, Chloe Clavel
Publié dans: ACII, 2016
Éditeur: IEEE

Automatically estimating emotion music using long-short term memory recurrent neural networks

Auteurs: Eduardo Coutinho, George Trigeorgis, Stefanos Zafeiriou, Björn Schuller
Publié dans: Interspeech, 2015
Éditeur: CEUR

Artificial Personality and Disfluency

Auteurs: M. Wester, M. Aylett, M. Tomalin, R. Dall
Publié dans: Interspeech, 2015
Éditeur: ISCA

Non-linear prediction with LSTM recurrent neural networks for acoustic novelty detection

Auteurs: Erik Marchi, Fabio Vesperini, Felix Weninger, Florian Eyben, Stefano Squartini, Björn Schuller
Publié dans: OJCNN, 2015
Éditeur: IEEE

The ICL-TUM-PASSAU approach for the MediaEval 2015 “Affective Impact of Movies” task

Auteurs: George Trigeorgis, Eduardo Coutinho, Fabien Ringeval, Erik Marchi, Stefanos Zafeiriou, Björn Schuller
Publié dans: Interspeech, 2015
Éditeur: CEUR

Learning to combine local models for Facial Action Unit detection

Auteurs: S. Jaiswal, B. Martinez, M.F. Valstar
Publié dans: FERA, 2015
Éditeur: IEEE

AVEC 2015 – The 5th International Audio/Visual Emotion Challenge and Workshop

Auteurs: Fabien Ringeval, Björn Schuller, Michel Valstar, Roddy Cowie, Maja Pantic
Publié dans: MM, 2015
Éditeur: ACM

Playing with Social and Emotional Game Companions

Auteurs: A. Chowanda, P. Blanchfield, M. Flintham and M.F. Valstar
Publié dans: IVA, 2016
Éditeur: Springer

Deep bidirectional long short-term memory recurrent neural networks for grapheme-to-phoneme conversion utilizing complex many-to many alignments

Auteurs: Amr El-Desoky Mousa, Björn Schuller
Publié dans: Interspeech, 2016
Éditeur: ISCA

The INTERSPEECH 2016 Computational Paralinguistics Challenge: Deception & Sincerity

Auteurs: Björn Schuller, Stefan Steidl, Anton Batliner, Julia Hirschberg, Judee K. Burgoon, Alice Baird, Aaron Elkins, Yue Zhang, Eduardo Coutinho, Keelan Evanini
Publié dans: ICMI, 2016
Éditeur: ISCA

AVEC 2016 – Depression, Mood, and Emotion Recognition Workshop and Challenge

Auteurs: Valstar, M.F., Gratch, J., Schuller, B., Ringeval, F., Lalanne, D., Torres Torres, M., Scherer, S., Stratou, G., Cowie, R. and Pantic, M
Publié dans: ACM Multimedia 2016, 2016
Éditeur: ACM

Speech analysis in the big data era

Auteurs: Björn Schuller
Publié dans: TSD, 2015
Éditeur: Springer

Deep Learning the Dynamic Appearance and Shape of Facial Action Units

Auteurs: S. Jaiswal, M.F. Valstar
Publié dans: IEEE WACV, 2016
Éditeur: IEEE

ChaLearn Looking at People and Faces of the World: Face Analysis Workshop and Challenge 2016

Auteurs: Escalera, S., Torres Torres, M., Martinez, B., Baró, X. and Escalante, H.J., Guyon I., Tzimiropoulos, G., Corneau, C., Oliu, M., Bagheri, M.A., Valstar, M.F.
Publié dans: CVPR, 2016
Éditeur: IEEE

Enhanced semi-supervised learning for multimodal emotion recognition

Auteurs: Zixing Zhang, Fabien Ringeval, Bin Dong, Eduardo Coutinho, Erik Marchi, Björn Schuller
Publié dans: ICASSP, 2016
Éditeur: IEEE

Does my speech rock? Automatic assessment of public speaking skills

Auteurs: Lucas Azais, Adrien Payan, Tianjiao Sun, Guillaume Vidal, Tina Zhang, Eduardo Coutinho, Florian Eyben, Björn Schuller
Publié dans: Interspeech, 2015
Éditeur: ISCA

Semi-autonomous data enrichment based on cross-task labelling of missing targets for holistic speech analysis

Auteurs: Yue Zhang, Yuxiang Zhou, Jie Shen, Björn Schuller
Publié dans: ICASSP, 2016
Éditeur: IEEE

An Open Source Kaldi Based Parametric Speech Synthesiser based on DNN

Auteurs: B. Potard, M. Aylett, D. Braude, P. Motlicek
Publié dans: Interspeech, 2016
Éditeur: ISCA

Adieu features? End-to-end apeech emotion recognition using a deep convolutional recurrent network

Auteurs: George Trigeorgis, Fabien Ringeval, Raymond Brückner, Erik Marchi, Mihalis Nicolaou, Björn Schuller, Stefanos Zafeiriou
Publié dans: ICASSP, 2016
Éditeur: IEEE

Sentiment analysis, opinion mining: on optimal parameters and performances

Auteurs: Björn Schuller, Amr El-Desoky Mousa, Vryniotis Vasileios
Publié dans: Wiley Interdisciplinary Reviews: Data Mining, Knowledge Discovery, 2015, ISSN 1942-4787
Éditeur: John Wiley and Sons Inc.

A deep matrix factorization method for learning attribute representations

Auteurs: George Trigeorgis, Konstantinos Bousmalis, Stefanos Zafeiriou, Björn Schuller
Publié dans: PAMI, 2016, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers

Cascaded Regression with Sparsified Feature Covariance Matrix for Facial Landmark Detection

Auteurs: E. Sánchez-Lozano, B. Martinez, M.F. Valstar
Publié dans: Pattern Recognition Letters, 2016, ISSN 0167-8655
Éditeur: Elsevier BV

L21-based regression and prediction accumulation across views for robust facial landmark detection

Auteurs: B. Martinez and M.F. Valstar
Publié dans: Image and Vision Computing, 2015, ISSN 0262-8856
Éditeur: Elsevier BV

From opinion mining to human-agent interaction

Auteurs: Chloé Clavel, Zoraida Callejas
Publié dans: IEEE TAC, 2016, ISSN 1949-3045
Éditeur: Institute of Electrical and Electronics Engineers

Grounding the detection of the user’s likes ´ and dislikes on the topic structure of human-agent interactions

Auteurs: Caroline Langlet, Chloe Clavel
Publié dans: KBS, 2016, ISSN 0950-7051
Éditeur: Elsevier BV

Context-Aware Automated Analysis and Annotation of Social Human-Agent Interactions

Auteurs: Tobias Baur, Gregor Mehlmann, Ionut Damian, Florian Lingenfelser, Johannes Wagner, Birgit Lugrin, Elisabeth André, Patrick Gebhard
Publié dans: ACM Transactions on Interactive Intelligent Systems (TiiS) 5.2, 2015, ISSN 2160-6455
Éditeur: Association for Computing Machinery (ACM)

Automatic estimation of biosignals from the human voice

Auteurs: Eduardo Coutinho, Björn Schuller
Publié dans: Science, Special Supplement on Advances in Computational Psychophysiology, 2015, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity

Advances, Challenges, and Opportunities in Automatic Facial Expression Recognition

Auteurs: B. Martinez and M.F. Valstar
Publié dans: Advances in Face Detection and Facial Image Analysis, 2016
Éditeur: Springer

Fostering user engagement in face-to-face human-agent interactions: a survey

Auteurs: Clavel, C., Cafaro, A., Campano, S., & Pelachaud, C.
Publié dans: Toward Robotic Socially Believable Behaving Systems-Volume II, 2016
Éditeur: Springer

Modeling User’s Social Attitude in a Conversational System

Auteurs: Tobias Baur, Dominik Schiller, Elisabeth André
Publié dans: Emotions and Personality in Personalized Services, 2016
Éditeur: Springer

Artificial Retrieval of Information Assistants - Virtual Agents with Linguistic Understanding, Social skills, and Personalised Aspects

Livrables

Publications

Partager cette page

Télécharger