BRAINS
Sept 2025 – Aug 2028
Neural, intelligent, and sustainable approaches for real-world scenarios.
PID2024-155948OB-C53 (AEI)
Alfonso Ortega
Speech Technologies, Natural Language Processing, and Machine Learning.
Academic research, international collaborations & Technology transfer.
Biography
Bridging Research and Industry.
Associate Professor at the University of Zaragoza, and Associate Director of Technology Transfer at the Aragon Institute for Engineering Research (I3A). As a member of the ViVoLab research group, my work focuses on Speech Technologies, Natural Language Processing, and Machine Learning, bridging the gap between theoretical research and real-world industrial application.
I am a Telecommunications Engineer (2000) and hold a PhD from the University of Zaragoza (2005), where I received the Extraordinary Doctorate Award and the Telefónica Chair Award. Currently, I'm the director of the BTS Chair (New Telecommunications Technologies) and the SAMCA Chair for Technological Development of Aragon, and serve as Secretary of the Thematic Network on Speech Technologies (RTTH) .
As Principal Investigator (PI), I lead two European projects (H2020 MSCA RISE action ESPERANTO ; DIH-WORLD Innovation Action) and supervise one MSCA-PF Grant. At the national level, I have been PI for nine National Plan projects, including one PROFIT, five State Program projects, two Networks of Excellence, and one Proof of Concept Project, while participating in 32 others. My commitment to technology transfer includes leading 14 industry-funded research contracts (participating in 49 total) and developing six international patents.
I have supervised four doctoral theses (awarded cum laude distinction) and hold five recognized six-year research periods (CNEAI-ANECA), including one transfer recognition. I have authored 39 publications in JCR-indexed journals, primarily in top-tier categories, with over 2,500 citations and an h-index of 27.
My international experience includes visiting researcher roles at the University of Texas at Dallas (2006) and Face In Motion in Porto (2015), as well as participation in the JSALT 2023 International Workshop organized by Johns Hopkins University. I was a member of the Steering Committee of the Aragón Digital Innovation Hub (selected as a European DIH 2020–2023) and, since January 2024, I coordinate the Digital Transition Hub at the University of Zaragoza for the UNITA European University alliance.
Activity Overview
25+
Years of Experience
60+
Publications
6
Int. Patents
20+
Projects as PI
Research
Competitive Research.
National and European initiatives in Speech Technology, Mental Health AI, and Multimedia Analysis.
MIND-CLARITY
Aug 2025 – Jul 2027
AI for Mental Illness Detection and Clinical Assessment with reliable interpretability.
MSCA Grant ID: 101206575
BEWORD
Sept 2022 – Feb 2026
Beyond the spoken word: Intelligent environments for multimedia understanding.
PID2021-126061OB-C44 (AEI)
AMIC-PoC: Affective Analysis Prototype
Dec 2021 – May 2024
Pre-competitive prototype for affective analysis of multimedia information.
PDC2021-120846-C41 (Ministry of Science)
ESPERANTO
Jan 2021 – Dec 2025
Explainable speech AI through international research staff exchanges.
Grant ID: 101007666
DIH-World
Sept 2021 – Apr 2022
Accelerating Digital Innovation Hubs across Europe.
Grant ID: 952176
2025
Journal Papers
Estevez, M.; Bonomi, C.; Ribas, D.; Ortega, A.; Ferrer, L.
Beyond Global Metrics: A Fairness Analysis for Interpretable Voice Disorder Detection Systems
JOURNAL OF VOICE, 2025
Conferences
Almudévar, A.; Hernández-Lobato, J. M.; Khurana, S.; Marxer, R.; Ortega, A.
Aligning Multimodal Representations through an Information Bottleneck
International Conference on Machine Learning (pp. 1250-1270). PMLR
2024
Preprints
Mingote, V.; Ortega, A.; Miguel, A.; Lleida, E.
Audio-visual speaker diarization: Current databases, approaches and challenges
arXiv preprint arXiv:2409.05659
Journal Papers
Vidal, J.; Ribas, D.; Bonomi, C.; Lleida, E.; Ferrer, L.; Ortega, A.
Automatic voice disorder detection from a practical perspective
JOURNAL OF VOICE, 2024
Conferences
Lebourdais, M.; Gimeno, P.; Mariotte, T.; Tahon, M.; Ortega, A.; Larcher, A.
3MAS: a multitask, multilabel, multidataset semi-supervised audio segmentation model
Proc. odyssey 2024 (pp. 232-239)
Gimeno, P.; Ortega, A.
Advances in Binary and Multiclass Audio Segmentation with Deep Learning Techniques: A PhD Thesis Overview
Proc. IberSPEECH 2024 (pp. 237-241)
Mariotte, T.; Almudévar, A.; Tahon, M.; Ortega, A.
An explainable proxy model for Multilabel audio segmentation
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 531-535). IEEE
Miguel A Pastor, Alfonso Ortega, Dayana Ribas
Analysis of the domain mismatch problem in the Speech Emotion Recognition Task
Proc. IberSPEECH 2024
Rubio Felipo, S.; Ribas González, D.; Lleida Solano, E.; Ortega Giménez, A.; Artiaga, A. M.
Assessing the Impact and Potential of TTS for Pathological Voice Data Augmentation on Pathology Detection Systems
Proc. IberSPEECH 2024 (pp. 41-45)
Mingote, V.; Ortega, A.; Miguel, A.; Lleida, E.
Encouraging Internal Representations with Speaker Information in End-to-End Neural Diarization by Adding Speaker Loss
Proc. IberSPEECH 2024 (pp. 191-195)
Lebourdais, M.; Mariotte, T.; Almudévar, A.; Tahon, M.; Ortega, A.
Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing.
In Proc. Interspeech 2024
Almudévar, A.; Mariotte, T.; Ortega, A.; Tahon, M.; Vicente, L.; Miguel, A.; Lleida, E.
Predefined Prototypes for Intra-Class Separation and Disentanglement
Proc. Interspeech 2024 (pp. 3809-3813)
María García Cutando, Eduardo Lleida Solano, Virginia Bazán Gil, Alfonso Ortega Giménez, Antonio Miguel Artiaga
Semantic Information Retrieval through Autonomous Agents
Proc. IberSPEECH 2024
Pastor, M. Á.; Ortega, A.; Miguel, A.; Ribas, D.
The ViVoLab System for the Odyssey Emotion Recognition Challenge 2024 Evaluation
Proc. odyssey 2024 (pp. 274-280)
Almudévar, A.; Mariotte, T.; Ortega, A.; Tahon, M.
Unsupervised multiple domain translation through controlled disentanglement in variational autoencoder
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7010-7014). IEEE
Teaching
Current Courses
Core subjects taught across graduate and undergraduate programs.
Speech Processing
Erasmus Mundus Master in Linguistic Data Science
2025 - PresentView Syllabus
Multimedia Processing & Interactivity
Degree in Telecommunications Technology Engineering
2024 - PresentView Syllabus
Speech & Language Technologies
Master in Telecommunications Engineering
2024 - PresentView Syllabus
Audio & Image Processing
Bachelor's Degree in Telecomm. Tech. & Services Engineering
2020 - PresentView Syllabus
Teaching History
2013 - 2024Multimedia Engineering & InteractivityBachelor's Degree in Telecomm. Tech. & Services Engineering
2015 - 2024Speech TechnologiesMaster's Degree in Telecommunications Engineering
2012 - 2020Digital Signal Processing ApplicationsBachelor's Degree in Telecomm. Tech. & Services Engineering
2011 - 2015Communication TheoryBachelor's Degree in Telecomm. Tech. & Services Engineering
2001 - 2014Data TransmissionTelecommunication Engineering
2007 - 2013S3-Speech Technologies IMaster's in IT & Mobile Comms Networks
2007 - 2013Ambient Intelligence & BiometryMaster's in Biomedical Engineering
2001 - 2011Advanced Digital CommunicationsTelecommunication Engineering / Master's in IT
2007 - 2009Digital Signal Processing LabTelecommunication Engineering
Contact
Contact
Back to topFor research collaborations, student supervision, or institutional inquiries, please reach out using the details below.
Office
Ada Byron Building, Office 3.03 María de Luna 1 50018 Zaragoza Spain
Phone
+34 976 76 23 63 ext. 842363
Office Hours
Wednesdays · 10:00–12:00 & Thursdays · 16:00–18:00
Available in person. Please email to confirm appointments.