Voice driven interaction in XR spaces

Informazioni relative al progetto

VOXReality

ID dell’accordo di sovvenzione: 101070521

DOI

10.3030/101070521

Progetto chiuso

Data della firma CE 11 Giugno 2022

Data di avvio 1 Ottobre 2022

Data di completamento 31 Dicembre 2025

Finanziato da

• Digital, Industry and Space

Costo totale

€ 4 786 875,00

Contributo UE

€ 4 786 875,00

Coordinato da

MAGGIOLI SPA
Italy

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (6)

Dissemination and communication plan

This report will outline communication and dissemination channels to be used and identify relevant events and publications.

Development infrastructure and integration guidelines

Analysis of the integration and validation requirements

Model deployment analysis V1

This deliverable will analyse the progress and results on VOXReality models deployment, training and XR applications.

Definition and Analysis of VOXReality Use Cases V1

Detailed analysis of use cases, technical and user requirements for each case of the project.

Advanced AI multi-modal for XR analysis V1

This deliverable will analyse the progress and results on VOXReality Audio processing, VOXReality Multilingual translation, Vision and language based XR models and Context aware generative dialogue system.

Open call documents collection V1

This deliverable will contain all the needed information and necessary documents for the applicants to submit applications to the Open Call.

Pubblicazioni

Peer reviewed articles (2)

Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues

Autori: Wentao Deng, Jiahuan Pei, Zhaochun Ren, Zhumin Chen, Pengjie Ren
Pubblicato in: Transactions of the Association for Computational Linguistics, Numero 11, 2023, ISSN 2307-387X
Editore: MIT Press
DOI: 10.1162/TACL_A_00599

SADAMB: Advancing Spatially-Aware Vision-Language Modeling Through Datasets, Metrics, and Benchmarks

Autori: Giorgos Papadopoulos, Petros Drakoulis, Athanasios Ntovas, Alexandros Doumanoglou, Dimitris Zarpalas
Pubblicato in: Computers, Numero 14, 2025, ISSN 2073-431X
Editore: MDPI AG
DOI: 10.3390/COMPUTERS14100413

Conference proceedings (10)

VOXReality: Immersive XR experiences

Autori: Maniatis, A., Bourou, S., Anastasakis, Z., Psychogios, K.
Pubblicato in: IHIET-AI 2023, Numero 70, 2023
Editore: AHFE (2023) International Conference. AHFE Open Access

Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models

Autori: Paweł Mąka, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
Pubblicato in: Proceedings of the 31st International Conference on Computational Linguistics, 2025
Editore: Association for Computational Linguistics

Enhancing the Audience Experience for VR and AR Theatre with AI-generated Subtitles

Autori: Irene Viola, Moonisa Ahsan, Olga Chatzifoti, Atanas Yonkov, Eleni Oikonomou, Ioannis Radin, Paweł Mąka, Abderrahmane Issam, Pablo Cesar
Pubblicato in: Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology, 2025
Editore: ACM
DOI: 10.1145/3756884.3766057

You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models

Autori: Pawel Maka, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
Pubblicato in: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.EMNLP-MAIN.1394

Sequence Shortening for Context-Aware Machine Translation

Autori: Mąka, P., Semerci, Y. C., Scholtes, J., & Spanakis, G.
Pubblicato in: Findings of the Association for Computational Linguistics: EACL 2024, 2024
Editore: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2402.01416

VRD: A multi-lingual translation and Ai-Assisted Navigation experience for VR Conference Application

Autori: Moonisa Ahsan, Irene Viola, Manuel Toledo, Dimitris Kontopoulos, Pablo Cesar
Pubblicato in: Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology, 2025
Editore: ACM
DOI: 10.1145/3756884.3768418

Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality

Autori: Jiahuan Pei, Irene Viola, Haochen Huang, Junxiao Wang, Moonisa Ahsan, Fanghua Ye, Jiang Yiming, Yao Sai, Di Wang, Zhumin Chen, Pengjie Ren, Pablo Cesar
Pubblicato in: 62nd Annual Meeting of the Association for Computational Linguistics, 2024
Editore: ACL 2024
DOI: 10.48550/ARXIV.2405.13034

Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters

Autori: Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
Pubblicato in: Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), 2024
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2024.IWSLT-1.36

DTW-Align: Bridging the Modality Gap in End-to-End Speech Translation with Dynamic Time Warping Alignment

Autori: Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
Pubblicato in: Proceedings of the Tenth Conference on Machine Translation, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.WMT-1.11

A Representation Level Analysis of NMT Model Robustness to Grammatical Errors

Autori: Abderrahmane Issam, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
Pubblicato in: Findings of the Association for Computational Linguistics: ACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-ACL.451

Book chapters (1)

Using Augmented Reality and Machine Learning for Captioning in Theatrical Experiences

Autori: Olga Chatzifoti, Nick Achilleopoulos, Spiros Borotis, Moonisa Ahsan, and Eleni Oikonomou
Pubblicato in: EuroXR 2024: Proceedings of the 21st EuroXR International Conference, Numero 322, 2024, ISSN 2242-1211
Editore: VTT Technical Research Centre of Finland
DOI: 10.32040/2242-122X.2024.T432