MENHIR member María Inés Torres is part of the Steering Committee of the CUI2022 conference, that will take place in Glasgow from 26th to 28th July 2020.

CUI 2022 aims to further develop a collaborative community around human-computer interaction issues in speech and language technology, with a specific interest in theory-based and applied scientific issues in the field of speech and text-based conversational user interfaces.

More information: https://www.conversationaluserinterfaces.org/2022/

Submission deadline: 23rd February 2022

MENHIR members Maurice Mulvenna and Jane Zheng from Ulster University are co-organizing the First International Workshop on Trustworthy AI for the Future of Risk Management (TAI-RM 2022) in Belfast on 14th June.

Topics

Potential topics include, but are not limited to, the following:

• Novel theoretical achievements for TAI methodology.
• Novel developments for existing TAI techniques.
• Practical deployment of TAI within different domains: best practices and lessons learned.
• Reviews highlighting important challenges and open problems within TAI.
• Case studies of use response to TAI techniques and AI model outputs.
• Novel datasets for use within the TAI in application community.
• Discussion on industry areas where how best to leverage TAI moving forward.
• TAI related regulation description and enforcement.

Sessión at NVIDIA GTC 2

Summary: Conversational AI applications are comprised of a hierarchy of deep learning natural language processing (NLP) models and speech technologies. Making these many different components work together to realize robust real-world applications a complex, both in terms of model interaction and computing resource orchestration. Deploying NLP models for processing speech requires end-to-end speech recognition, appropriate segmentation, and robust NLP model training processes that can cope with speech recognition transcription errors. In addition, effective conversational AI applications rely on numerous preprocessing models such as punctuation restoration, true casing, question classification, negation, and many others to ensure robust operation and reduction of false positives. We’ll present real-world contact center and medical consultation decision support cases to illustrate how such complex conversational AI ecosystems should be constructed.

Presenter: Nigel Cannings, CTO, Intelligent Voice, Ltd.

Join for free here: https://www.nvidia.com/gtc/session-catalog/?search=S41145&search=S41145%2C%20S41145&tab.scheduledorondemand=1583520458947001NJiE&utm_content=201705046&utm_medium=social&utm_source=twitter&hss_channel=tw-164683799#/session/1634832058529001pf9B

On February 23-24, the “Cancer Survivorship – AI for Well-being” (CS_AIW) Cluster will hold its 4th Meeting of Minds, the first to be open to the public, as patients and survivors will be part of the audience. In fact, the event will revolve around the question “How can new technologies better support patients?“.

More information: https://www.h2020-faith.eu/2022/01/new-technology-in-cancer-care-cs_aiw-cluster-mom-4/

Register here: https://www.eventbrite.it/e/251100707977

MENHIR coordinator Zoraida Callejas will participate in a roundtable about natural language processing in international projects organized by the DiverTLes community (Diversity in Language Technologies in Spain).

More info: https://gplsi.dlsi.ua.es/pln/node/550

In Spanish:

La comunidad DiverTLes: Diversidad en Tecnologías del Lenguaje en España, iniciativa dentro del marco de la red temática de excelencia PLNnet, se complace en presentar la Mesa redonda “PLN en proyectos internacionales” que se celebrará virtualmente el próximo 18 de enero a las 17.30 horas.

En esta ocasión contaremos con 3 ponentes (Zoraida Calleja, Elena González y Elena Lloret) que actualmente se encuentran implicadas en interesantes proyectos internacionales en los que las tecnologías del lenguaje juegan un papel importante. Las ponentes nos presentarán sus proyectos y podremos comentar diferentes aspectos. En esta ocasión la mesa será moderada por Encarna Segarra, profesora e investigadora en PLN de la Universidad Politécnica de Valencia. Cada una de las ponentes expondrá su trabajo durante 5-7 minutos para posteriormente establecer un debate entre los asistentes que podrán plantear preguntas, dudas o apreciaciones. El tiempo estimado para todo el evento será de una hora en total.

Para asistir al evento gratuito hace falta inscripción a través de este formulario y recibiréis directamente los datos de conexión a la mesa redonda a través de Google Meet.

Following the successful ACM In-Cooperation CUI conferences in 2019 and 2020, CUI 2021 will be a hybrid conference with sessions online and in person in Bilbao, Spain. The conference will run from 27–29 July 2021.

Topics relevant to the conference include, but are not limited to:

• voice user experience
• speech interfaces
• speech interface theory development
• conversational interaction through technology
• text-based conversational interfaces
• chatbots
• speech synthesis
• speech recognition
• dialogue management
• conversational interface design insights
• conversational search
• methods for conversational user interface development and evaluation
• multimodal interaction involving speech, text or other language based interfaces

More information: https://www.conversationaluserinterfaces.org/2021/

Involvement of MENHIR participants:

• General co-chair: María Inés Torres
• Co-assistant to the general chairs: Raquel Justo
• Programme Committee: Zoraida Callejas, Anna Esposito, Raquel Justo, María Inés Torres

THE EUROPEAN CHATBOT & CONVERSATIONAL AI SUMMIT
IBEROAMERICAN EDITION

Home

MENHIR participants Michael McTear (Ulster University), David Griol (University of Granada) and Zoraida Callejas (University of Granada) will speak at the European Chatbot & Conversational AI Summit- IberoAmerican Edition, a two days virtual conference and exhibition designed to host industry executives, and adopters of Conversational AI, Chatbots, speech or voice technology, UX design , NLP & Virtual Assistant . The summit will reflect the latest tendencies and recent application changes in the Conversational AI space in the Iberoamerican market.

#EUfunded #H2020 research projects @H2020_Faith, @MenhirH2020 and @OncoRelief come together in a virtual joint workshop to gather feedback on their #usercentric#healthcare solutions in support of people suffering from poor #MentalHealth. Follow us for updates

e-Coaches are promising intelligent systems that aims at supporting human everyday life, dispatching advices through different interfaces, such as apps, conversational interfaces and augmented reality interfaces. This workshop aims at exploring how e-coaches might benefit from spatially and time-multiplexed interfaces and from different communication modalities (e.g., text, visual, audio, etc.) according to the context of the interaction.

This workshop is co-organized by several EU consortia who are currently developing e-coaches in the context of the H2020 programme. Please check the Organizers page for the full list.

For further details on how to participate please read the Call for Papers. We invite researchers interested to share their ideas and findings in this field to submit a paper by August 31, 2020 on EasyChair. An extension is possible upon request by email.

The workshop is held in conjunction with the 22^nd ACM Conference on Multimodal Interaction scheduled for 25-29 October 2020 in Utrecht, The Netherlands. Due to COVID-19 the conference and this workshop might be held remotely.

More info: https://multimodal-ecoches.nestore-coach.eu/home

https://www.springer.com/journal/10044/updates/17569830

Recent advances in technology have boosted the development and release of active assistive living devices, based on wearable and/or non-obtrusive visual and multi-modal signals for e-health and welfare support. These solutions are seamlessly integrated in the environment, such as sensor-based systems installed in elderly people’s homes for ambient monitoring and intelligent visual warning.

In addition, research on ubiquitous computing has favored the implementation of more user-centered applications such as virtual tutoring, coaching agents, physical rehabilitation and psychological therapy systems. To allow these systems to provide features that satisfy the user’s requirements, expectations, and acceptance, the tendency is now shifting towards the conception of empathic solutions, tailored to personalized user needs. The new assistive systems must be able to understand user’s behaviors, mood and intentions, and react to them accordingly in real time, as well as detect timely changes in behaviors and health states. Furthermore, such systems are expected to infer the user’s traits, attitudes and psychological profile to deliver a more personalized user-machine interaction. These solutions require advanced computer vision and machine learning techniques, such as facial expression analysis, gaze and pose estimation, and gesture recognition, in addition to behavioral and psychological theories for modeling individual’s profiles. While these tasks are currently obtaining outstanding performances in controlled and prototypical environments (e.g., detection of facial expressions of emotion on static faces), the challenge falls on their integration and application in naturalistic scenarios, where extensive sources of variability (pose, age, behaviors, moods, illumination conditions, dynamic speaking emotional faces, among others) affect the processing of the detected signals.

The Computer Vision and Machine Learning for Healthcare Applications special issue aims to collect latest approaches and findings, as well as to discuss the current challenges of machine learning and computer vision based e-health and welfare applications. The focus is on the employment of single or multi-modal face, gesture and pose analysis. We expect this special issue to increase the visibility and importance of this area, and contribute, in the short term, in pushing the state of the art in the automatic analysis of human behaviors for health and wellbeing applications.

Topics of interest include, but are not limited to:

• Multi-modal integration
• Psychological profiling from (audio)-visual and/or multi-modal data
• Approaches based on psychology behavioral models
• Mobile-based and human-computer interaction applications
• User-understanding in human-computer interaction
• Human behavior analysis for health and well-being support
• Assistive technologies for supporting vulnerable people
• Virtual avatars and coaching
• Physical and psychological therapy systems
• Assistive care
• User acceptance of empathic assistive systems
• Real-time applications
• Datasets

Important dates 

Paper submission deadline: extended to 14 September 2020 (final deadline)
Acceptance notification: 30th November 2020.
Tentative publication date: January 2021

Guest Editors
Sergio Escalera, Computer Vision Center (UAB) and Universitat de Barcelona, sergio@maia.ub.es
Cristina Palmero, Universitat de Barcelona and Computer Vision Center (UAB), crpalmec7@alumnes.ub.edu
Maria Inés Torres, University of the Basque Country (UPV/EHU) and SPIN RG, manes.torres@ehu.es
Anna Esposito, Behaving Cognitive System Lab, Department of Psychology, Università della Campania “Luigi Vanvitelli” and International Institute for Advanced Scientific Studies (IIASS), Italy, iiass.annaesp@tin.it
Alexa Moseguí Saladié, Universitat de Barcelona and Computer Vision Center (UAB), amosegui@cvc.uab.es

Advisory Editors
Bjorn W. Schuller, http://www.schuller.one/, schuller@tum.de
Jeffrey Cohn, http://www.jeffcohn.net/, jeffcohn@pitt.edu

CUI 2020, organized by MENHIR’s partner UPV/EHU

Home

23, 24 July 2020, Bilbao (Spain)

Based on a successful inaugural ACM In Co-Operation conference in 2019, CUI 2020 aims to further develop a collaborative community around human-computer interaction issues in speech and language technology, with specific interest in theory based and applied scientific issues in the field of speech and text based conversational user interfaces. CUI 2020 looks to bring together relevant communities (e.g. ISCA, ACM SIGCHI, CogSci) to publish, disseminate and showcase high quality cutting edge research related to the field, promote insight and debate in this interesting and important discipline within language interfaces.

Topics relevant to the conference include, but are not limited to:

• voice user experience
• speech interfaces
• speech interface theory development
• conversational interaction through technology
• text-based conversational interfaces
• chatbots
• speech synthesis
• speech recognition
• dialogue management
• conversational interface design insights
• conversational search
• methods for conversational user interface development and evaluation
• multimodal interaction involving speech, text or other language based interfaces

MENHIR is involved in the organization of the special session: BEhavINg coGnitive Systems: Believable, Autonomous, Adaptive, Context Aware (BEINGS) Track at the 1st IEEE International Conference on Human-Machine Systems, which will be held in Rome from 6th to 8th April 2020.

Chairs:

Anna Esposito, Università della Campania “Luigi Vanvitelli”, Italy.
Maria Inés Torres, Universidad País Vasco UPV/EHU, Spain
Zoraida Callejas Carrión, Universidad de Granada, Spain
Antonietta M. Esposito, Istituto Nazionale di Geofisica e Vulcanologia, Sez. di Napoli, Osservatorio Vesuviano, Italy.
Gennaro Cordasco, Università della Campania “Luigi Vanvitelli”, Italy
Sergio Escalera, Universitat de Barcelona and Computer Vision Center, Spain
Carl Vogel, Trinity College Dublin, School of Computer Science and Statistics, Ireland

Description:
The integration of cognitive theories, knowledge representation models and algorithms in a computational framework will enable rich models of human-machine interaction, and the development of novel machine learning techniques for the analysis of socially situated multimodal human communication streams. The successful analysis, modelling, and understanding of context effects on social interactions will be of high relevance for ICT applications where human-machine communication is particularly emphasized.
In order to enable the development of computational paradigms for implementing  socially believable, emotionally adaptive, and  context-aware systems (BEINGS) able to enhance quality of life in society, expertise in different yet complementary scientific fields must be accounted for. A holistic scientific approach, cross-cultural collaborations and exchanges are required. To this aim, this track is promoting contributions across a spectrum of disciplines reporting on  experimental data , theories, and mathematical models of dynamics of signal exchanges (in terms of shared meanings, emotional states, cultural differences, and cognitive processes of cooperation, and decision making). The ultimate goal is to equip machines with human level automaton intelligence.

Topics:
The topics include, but are not limited to:

• Cross-cultural processing of social signals
• Linguistic and social interactional exchanges
• Social Robotics: analysis and applications
• Human behaviour: Analysis and understanding
• Linguistic sentiment analysis
• Changes in sentiment expressions
• Cognitive Economy
• Group behaviour, group cognition and cultural specificity
• Influence of context on perception, memory and decision making
• Cognitive systems for multimodal signal analysis
• Nonlinear processing of audio-video social signals
• Multimodal social signal processing
• New datasets and forms of data that can push the research in the field
• Predictive bias analysis
• Adaptation and adaptive algorithms
• Emotions: analyses, detection, recognition
• Assistive technologies and user’s acceptance
• Age, gender, and personality traits’ effects

Important Dates

CUI 2020 – 2nd International Conference on Conversational User Interfaces
Bilbao, Spain | 23-24 July 2020
www.cui2020.com
@CUI_Conference

**** 13th March 2020 @ 23:59 GMT+1 – submission deadline ****

CUI 2020 is looking for original contributions from a broad range of disciplines including: human-computer interaction, computer science, engineering, speech technology, linguistics, psychology, cognitive sciences and sociology. Topics include, but are not limited to:

– voice user experience
– speech interfaces
– speech interface theory development
– conversational interaction through technology
– text-based conversational interfaces
– chatbots
– speech synthesis
– speech recognition
– dialogue management
– conversational interface design insights
– conversational search
– methods for conversational user interface development and evaluation
– multimodal interaction involving speech, text or other language based interfaces

**** Submission format and instructions ****

Provocation Papers – https://protection.puc.rediris.es/fmlurlsvc/?fewReq=:B:JVw4MzAxOCR0PzMsMiRrZj8yMzgyMyRxa2VsY3Z3cGc/MTJjNWExMDNhN2EyZGExNzc3MGM0MztgYDBmZDZjNDphYTU0ZjE1NSR2PzM3OjA0NDM0MTMkc2tmPzIzUklDS0NLMjIwMjQ0LzIzUklDS0NJMjIwMjQ0JHBhcnY/JGE/Mg==&url=https%3a%2f%2fcui2020.com%2fprovocation-papers < https://protection.puc.rediris.es/fmlurlsvc/?fewReq=:B:JVw4MzAxOCR0PzMsMiRrZj8yMzgyMyRxa2VsY3Z3cGc/MTJjNWExMDNhN2EyZGExNzc3MGM0MztgYDBmZDZjNDphYTU0ZjE1NSR2PzM3OjA0NDM0MTMkc2tmPzIzUklDS0NLMjIwMjQ0LzIzUklDS0NJMjIwMjQ0JHBhcnY/JGE/Mg==&url=https%3a%2f%2fcui2020.com%2fprovocation-papers >

CUI 2020 Provocation Papers are short papers that explore controversial, risk taking or nascent ideas that have the potential to spark debate and discussion at the conference.

2 page anonymised papers (excluding references) using the current ACM proceedings template (LaTeX submissions should use the sigconf format). Each paper will be anonymously peer reviewed by 3 expert reviewers. Submissions must be made using the EasyChair website: https://easychair.org/conferences/?conf=cui2020 < https://easychair.org/conferences/?conf=cui2020 >. Accepted Provocation Papers will be archived in the ACM Digital Library and authors be given an oral presentation slot at the conference.

Posters & Demos – https://protection.puc.rediris.es/fmlurlsvc/?fewReq=:B:JVw4MzAxOCR0PzMsMiRrZj8yMzgyMyRxa2VsY3Z3cGc/M2BgOjBhYzQ6MTEwMzAwZ2czMTsxZDY0YGEyM2dgNzM1NTFhYGExMSR2PzM3OjA0NDM0MTMkc2tmPzIzUklDS0NLMjIwMjQ0LzIzUklDS0NJMjIwMjQ0JHBhcnY/JGE/Mg==&url=https%3a%2f%2fcui2020.com%2fposters-demos < https://protection.puc.rediris.es/fmlurlsvc/?fewReq=:B:JVw4MzAxOCR0PzMsMiRrZj8yMzgyMyRxa2VsY3Z3cGc/M2BgOjBhYzQ6MTEwMzAwZ2czMTsxZDY0YGEyM2dgNzM1NTFhYGExMSR2PzM3OjA0NDM0MTMkc2tmPzIzUklDS0NLMjIwMjQ0LzIzUklDS0NJMjIwMjQ0JHBhcnY/JGE/Mg==&url=https%3a%2f%2fcui2020.com%2fposters-demos >

Demo/Poster Papers are interactive contributions (Demos) and early stage research (Posters) aiming to tackle challenges and show progress in the field of Conversational User Interfaces.

2-4 page anonymised papers (excluding references) using the current ACM proceedings template. (LaTeX submissions should use the sigconf format). Each paper will be anonymously peer reviewed by 3 expert reviewers. Submissions must be made using the EasyChair website: https://easychair.org/conferences/?conf=cui2020 < https://easychair.org/conferences/?conf=cui2020 >. Accepted Provocation Papers will be archived in the ACM Digital Library and authors be given an oral presentation slot at the conference.

**** Important dates ****

13th March – Submission deadline

17th April – Notification to authors

24th April – Camera ready version

**** About CUI 2020 ****

There has been an increasing interest in language based interactions with technology. Driven by the commercial success of intelligent personal assistant devices such as Alexa and Google Home, to the growth of the use of chatbots in commercial settings, the number of natural language and conversation based interactions is growing. Based on a successful inaugural ACM In-Cooperation conference in 2019, CUI 2020 aims to further develop a collaborative community around human-computer interaction issues in speech and language technology, with specific interest in theory based and applied scientific issues in the field of speech and text based conversational user interfaces. CUI 2020 looks to bring together relevant communities (e.g. ISCA, ACM SIGCHI, CogSci) to publish, disseminate and showcase high quality cutting edge research related to the field, promote insight and debate in this interesting and important discipline within language interfaces.

**** Organising committee ****

María Inés Torres (Universidad del País Vasco, UPV/EHU, Spain)
Stephan Schlögl (MCI Management Center, Innsbruck, Austria)
Benjamin Cowan (University College Dublin, Ireland)
Heloisa Candello (IBM Research Lab, Brazil)
Stuart Reeves (University of Nottingham, UK)
Minha Lee (Eindhoven University of Technology, Netherlands)
Cornelius Glackin (Intelligent Voice Ltd.)
Cosmin Munteanu (University of Toronto Mississauga, Canada)
Donald McMillan (Stockholm University, Sweden)
Janice Tsai (Mozilla, USA)
Martin Porcheron (University of Nottingham, UK)
Moira McGregor (Stockholm University, Sweden)
Christine Murad (University of Toronto, Canada)
Asier López-Zorrilla (Universidad del País Vasco, UPV/EHU, Spain)
Leigh Clark (Swansea University, UK)
Raquel Justo (Universidad del País Vasco, UPV/EHU, Spain)
Javier Mikel Olaso (Universidad del País Vasco, UPV/EHU, Spain)
Leila Ben Letaifa Zouari (University of Sousse, Tunisia)

The ECMH want to increase collaboration between service users and professionals in different fields. ECMH believe that services and care processes can be improved with respectful collaboration between different parties. In our conferences every participant’s voice is as important. We give arena for research, practice development, projects and personal experiences. We always have close collaboration with local partners in psychiatric hospitals, universities and service user associations.

The 2019 ECMH Conference is in Belfast, Northern Ireland. Ulster University with the MENHIR consortium has helped arrange a special session on ‘Chatbots in Mental Health’ at the conference.

Organised by Prof Lauri Kuosmanen from University of Eastern Finland, and hosted by Prof Maurice Mulvenna and Dr Raymond Bond from Ulster University, this will comprise 4 discussions with a follow-on Q&A session on the value and context of chatbots in a mental health setting.

The special session includes the following papers:

• Mental Health in the workplace: Using chatbots for self-assessment, Gillian Cameron, Inspire Wellbeing
• Towards a chatbot assisted mental health and wellbeing ecosystem, Brian Cahill, Cork Institute of Technology
• Chatbots for mental health and suicide prevention: is this even ethical? Professor Siobhan O’Neill, Ulster University
• Towards Conversational Coaching Agents to Support Bibliotherapy Sessions, Dr Patrick McAllister, Verbal Arts

Special Session at Interspeech 2019

Research devoted to understanding the relationship between verbal and nonverbal communication modes, and investigating the perceptual and cognitive processes involved in the coding/decoding of emotional states is particularly relevant in the fields of Human-Human and Human-Computer Interaction.

When it comes to speech, it is unmistakable that the same linguistic expression may be uttered for teasing, challenging, stressing, supporting, inquiring, answering or as expressing an authentic doubt. The appropriate continuance of the interaction depends on detecting the addresser’s mood.

To progress towards a better understanding of such interactional facets, more accurate solutions are needed for defining emotional and empathic contents underpinning daily interactional exchanges, developing signal processing algorithms able to capture emotional features from multimodal social signals and building mathematical models integrating emotional behaviour in interaction strategies.

The themes of this special session are multidisciplinary in nature and closely connected in their final aims to identify features from realistic dynamics of emotional speech exchanges. Of particular interest are analyses of visual, textual and audio information and corresponding computational efforts to automatically detect and interpret their semantic and pragmatic contents.

A special issue of the Journal Computer Speech and Language is foreseen as an outcome of this special session.

Details can be found on the web page: http://www.empathic-project.eu/index.php/ssinterspeech2019/

Organizers:

ANNA ESPOSITO (iiass.annaesp@tin.it; anna.esposito@unicampania.it) – MENHIR
MARIA INÉS TORRES (manes.torres@ehu.eus) – MENHIR
OLGA GORDEEVA (olga.gordeeva@acapela-group.com)
RAQUEL JUSTO (raquel.justo@ehu.eus) – MENHIR
ZORAIDA CALLEJAS CARRIÓN (zoraida@ugr.es) – MENHIR
KRISTIINA JOKINEN (kristiina.jokinen@aist.go.jp
GENNARO CORDASCO (gennaro.cordasco@unicampania.it) – MENHIR
BJOERN SCHULLER (bjoern.schuller@imperial.ac.uk)
CARL VOGEL (vogel@cs.tcd.ie)
ALESSANDRO VINCIARELLI (Alessandro.Vinciarelli@glasgow.ac.uk)
GERARD CHOLLET (gerard.chollet@telecom-paristech.fr) – MENHIR
NEIL GLACKIN (neil.glackin@intelligentvoice.com) – MENHIR

María Inés Torres (UPV) will give a lecture on VoiceBots in the RTTH Summer School 2019 (RTTHSS2019). The school is sponsored by the Spanish Red Temática en Tecnologías del Habla (RTTH) and organized by the Speech and Natural Language Technologies Department of Vicomtech. The RTTHSS2019 will take place in Donostia-San Sebastián (Spain), from July 2nd to July 5th 2019.

More info: RTTHSS2019 web page