AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2025
Mendoza, A. P.; Quiroga, K. J. Barrios; Celis, S. D. Solano; M., C. G. Quintero
NAIA: A Multi-Technology Virtual Assistant for Boosting Academic Environments—A Case Study Journal Article
In: IEEE Access, vol. 13, pp. 141461–141483, 2025, ISSN: 21693536 (ISSN), (Publisher: Institute of Electrical and Electronics Engineers Inc.).
Abstract | Links | BibTeX | Tags: Academic environment, Artificial intelligence, Case-studies, Computational Linguistics, Computer vision, Digital avatar, Digital avatars, Efficiency, Human computer interaction, Human-AI Interaction, Interactive computer graphics, Language Model, Large language model, large language model (LLM), Learning systems, Natural language processing systems, Personal digital assistants, Personnel training, Population statistics, Speech communication, Speech processing, Speech to text, speech to text (STT), Text to speech, text to speech (TTS), user experience, User interfaces, Virtual assistant, Virtual assistants, Virtual Reality
@article{mendoza_naia_2025,
title = {NAIA: A Multi-Technology Virtual Assistant for Boosting Academic Environments—A Case Study},
author = {A. P. Mendoza and K. J. Barrios Quiroga and S. D. Solano Celis and C. G. Quintero M.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105013598763&doi=10.1109%2FACCESS.2025.3597565&partnerID=40&md5=7ad6b037cfedb943fc026642c4854284},
doi = {10.1109/ACCESS.2025.3597565},
issn = {21693536 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {IEEE Access},
volume = {13},
pages = {141461–141483},
abstract = {Virtual assistants have become essential tools for improving productivity and efficiency in various domains. This paper presents NAIA (Nimble Artificial Intelligence Assistant), an advanced multi-role and multi-task virtual assistant enhanced with artificial intelligence, designed to serve a university community case study. The system integrates AI technologies including Large Language Models (LLM), Computer Vision, and voice processing to create an immersive and efficient interaction through animated digital avatars. NAIA features five specialized roles: researcher, receptionist, personal skills trainer, personal assistant, and university guide, each equipped with specific capabilities to support different aspects of academic life. The system’s Computer Vision capabilities enable it to comment on users’ physical appearance and environment, enriching the interaction. Through natural language processing and voice interaction, NAIA aims to improve productivity and efficiency within the university environment while providing personalized assistance through a ubiquitous platform accessible across multiple devices. NAIA is evaluated through a user experience survey involving 30 participants with different demographic characteristics, this is the most accepted way by the community to evaluate this type of solution. Participants give their feedback after using one role of NAIA after using it for 30 minutes. The experiment showed that 90% of the participants considered NAIA-assisted tasks of higher quality and, on average, NAIA has a score of 4.27 out of 5 on user satisfaction. Participants particularly appreciated the assistant’s visual recognition, natural conversation flow, and user interaction capabilities. Results demonstrate NAIA’s capabilities and effectiveness across the five roles. © 2025 Elsevier B.V., All rights reserved.},
note = {Publisher: Institute of Electrical and Electronics Engineers Inc.},
keywords = {Academic environment, Artificial intelligence, Case-studies, Computational Linguistics, Computer vision, Digital avatar, Digital avatars, Efficiency, Human computer interaction, Human-AI Interaction, Interactive computer graphics, Language Model, Large language model, large language model (LLM), Learning systems, Natural language processing systems, Personal digital assistants, Personnel training, Population statistics, Speech communication, Speech processing, Speech to text, speech to text (STT), Text to speech, text to speech (TTS), user experience, User interfaces, Virtual assistant, Virtual assistants, Virtual Reality},
pubstate = {published},
tppubtype = {article}
}
Virtual assistants have become essential tools for improving productivity and efficiency in various domains. This paper presents NAIA (Nimble Artificial Intelligence Assistant), an advanced multi-role and multi-task virtual assistant enhanced with artificial intelligence, designed to serve a university community case study. The system integrates AI technologies including Large Language Models (LLM), Computer Vision, and voice processing to create an immersive and efficient interaction through animated digital avatars. NAIA features five specialized roles: researcher, receptionist, personal skills trainer, personal assistant, and university guide, each equipped with specific capabilities to support different aspects of academic life. The system’s Computer Vision capabilities enable it to comment on users’ physical appearance and environment, enriching the interaction. Through natural language processing and voice interaction, NAIA aims to improve productivity and efficiency within the university environment while providing personalized assistance through a ubiquitous platform accessible across multiple devices. NAIA is evaluated through a user experience survey involving 30 participants with different demographic characteristics, this is the most accepted way by the community to evaluate this type of solution. Participants give their feedback after using one role of NAIA after using it for 30 minutes. The experiment showed that 90% of the participants considered NAIA-assisted tasks of higher quality and, on average, NAIA has a score of 4.27 out of 5 on user satisfaction. Participants particularly appreciated the assistant’s visual recognition, natural conversation flow, and user interaction capabilities. Results demonstrate NAIA’s capabilities and effectiveness across the five roles. © 2025 Elsevier B.V., All rights reserved.
Furukawa, O.
Implementation of Voice-Controlled Remote Measurements via Metaverse using Automatic Speech Recognition Journal Article
In: IEEJ Transactions on Fundamentals and Materials, vol. 145, no. 10, pp. 294–300, 2025, ISSN: 03854205 (ISSN); 13475533 (ISSN), (Publisher: Institute of Electrical Engineers of Japan).
Abstract | Links | BibTeX | Tags: Automatic speech recognition, digital twin, Fiber Sensor, Language Model, Large language model, Measurement system, Measurements instruments, Metaverse, Metaverses, optical fiber sensor, Optical-, Recognition methods, Remote measurement, Speech communication, Speech recognition
@article{furukawa_implementation_2025,
title = {Implementation of Voice-Controlled Remote Measurements via Metaverse using Automatic Speech Recognition},
author = {O. Furukawa},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105017845175&doi=10.1541%2Fieejfms.145.294&partnerID=40&md5=53e5584cc5d71588ca02c5ec820addd1},
doi = {10.1541/ieejfms.145.294},
issn = {03854205 (ISSN); 13475533 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {IEEJ Transactions on Fundamentals and Materials},
volume = {145},
number = {10},
pages = {294–300},
abstract = {Research on the three-dimensional virtual space “metaverse” is being actively conducted. The metaverse allows communication between distant “people” through voice and/or gestures. Applying the metaverse to distant “objects” is expected to bring industrial innovation. The industrial metaverse can be implemented in remote measurement systems. In previous research, we successfully controlled a measurement instrument using voice control via the metaverse. However, appropriate automatic speech recognition methods for metaverse measurement instruments have not been explored. In this study, we investigate the performance of representative automatic speech recognition methods that use deep neural networks, including Google Speech-to-Text and Faster-Whisper, an end-to-end generative pretrained transformer. In the case of dedicated control commands with the prefix, high performance was achieved with an average word error rate of 2%. Based on the results, we developed a measurement system and successfully demonstrated that it is possible to control measurement instruments in remote sites via the metaverse. © 2025 Elsevier B.V., All rights reserved.},
note = {Publisher: Institute of Electrical Engineers of Japan},
keywords = {Automatic speech recognition, digital twin, Fiber Sensor, Language Model, Large language model, Measurement system, Measurements instruments, Metaverse, Metaverses, optical fiber sensor, Optical-, Recognition methods, Remote measurement, Speech communication, Speech recognition},
pubstate = {published},
tppubtype = {article}
}
Research on the three-dimensional virtual space “metaverse” is being actively conducted. The metaverse allows communication between distant “people” through voice and/or gestures. Applying the metaverse to distant “objects” is expected to bring industrial innovation. The industrial metaverse can be implemented in remote measurement systems. In previous research, we successfully controlled a measurement instrument using voice control via the metaverse. However, appropriate automatic speech recognition methods for metaverse measurement instruments have not been explored. In this study, we investigate the performance of representative automatic speech recognition methods that use deep neural networks, including Google Speech-to-Text and Faster-Whisper, an end-to-end generative pretrained transformer. In the case of dedicated control commands with the prefix, high performance was achieved with an average word error rate of 2%. Based on the results, we developed a measurement system and successfully demonstrated that it is possible to control measurement instruments in remote sites via the metaverse. © 2025 Elsevier B.V., All rights reserved.