Email: lleida@unizar.es
Address: Ada Byron Building, María de Luna 1, 50018, Zaragoza, Spain
Principal Researcher and Head of VIVOLAB
Professor of Electrical Engineering
Vivolab, University of Zaragoza Aragón Institute for Engineering Research (I3A)
ABOUT ME
Eduardo Lleida received the M.Sc. degree in telecommunication engineering and the Ph.D. degree in signal processing from the Universitat Politcnica de Catalunya (UPC), Barcelona, Spain, in 1985 and 1990, respectively. From 1986 to 1988, he was involved in his doctoral work in the Department of Signal Theory and Communications, UPC. From 1989 to 1990, he was an Assistant Professor, and from 1991 to 1993, he was an Associated Professor in the Department of Signal Theory and Communications, UPC. From February 1995 to January 1996, he was with AT&T Bell Laboratories, Murray Hill, NJ, USA, as a Consultant in speech recognition.
He is currently a full Professor of signal theory and communications in the Department of Electronic Engineering and Communications, University of Zaragoza, Zaragoza, Spain, and a member of the Aragón Institute for Engineering Research, where he is heading the ViVoLab research group in speech technologies. He has been the doctoral advisor of 12 doctoral students. He has managed more than 50 speech-related projects, being inventor in six worldwide patents, and coauthored more than 200 technical papers in the field of speech, speaker and language recognition, speech enhancement and recognition in adverse acoustic environments, acoustic modeling, confidence measures, and spoken dialogue systems.
PUBLICATIONS
2023
Mingote, Victoria; Miguel, Antonio; Ortega, Alfonso; Lleida, Eduardo
Class token and knowledge distillation for multi-head self-attention speaker verification systems Artículo de revista
En: Digital Signal Processing, vol. 133, pp. 103859, 2023.
@article{nokey,
title = {Class token and knowledge distillation for multi-head self-attention speaker verification systems},
author = {Victoria Mingote and Antonio Miguel and Alfonso Ortega and Eduardo Lleida},
doi = {10.1016/j.dsp.2022.103859},
year = {2023},
date = {2023-03-01},
urldate = {2022-12-01},
journal = {Digital Signal Processing},
volume = {133},
pages = {103859},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Ribas, Dayana; Miguel, Antonio; Ortega, Alfonso; Lleida, Eduardo
On the Problem of Data Availability in Automatic Voice Disorder Detection. Conferencia
Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) – Volume 5: HEALTHINF, 2023, ISBN: 978-989-758-631-6.
@conference{Ribas2023b,
title = {On the Problem of Data Availability in Automatic Voice Disorder Detection.},
author = {Dayana Ribas and Antonio Miguel and Alfonso Ortega and Eduardo Lleida},
isbn = {978-989-758-631-6},
year = {2023},
date = {2023-02-13},
urldate = {2023-02-13},
booktitle = {Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 5: HEALTHINF},
pages = {330-337},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Ribas, Dayana; Pastor, Miguel; Miguel, Antonio; Martínez, David; Ortega, Alfonso; Lleida, Eduardo
Automatic Voice Disorder Detection using Self-Supervised Representations Artículo de revista
En: IEEE Access, vol. 11, pp. 14915-14927, 2023.
@article{Ribas2023,
title = {Automatic Voice Disorder Detection using Self-Supervised Representations},
author = {Dayana Ribas and Miguel Pastor and Antonio Miguel and David Martínez and Alfonso Ortega and Eduardo Lleida},
doi = {10.1109/ACCESS.2023.3243986},
year = {2023},
date = {2023-02-10},
urldate = {2023-02-10},
journal = {IEEE Access},
volume = {11},
pages = {14915-14927},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2022
Gimeno, Pablo; Ortega, Alfonso; Miguel, Antonio; Lleida, Eduardo
A Study on the Use of wav2vec Representations for Multiclass Audio Segmentation Conferencia
Proceedings of XII Jornadas en Tecnología del Habla and VIII Iberian SLTech (Iberspeech), 2022.
@conference{Gimeno2022b,
title = {A Study on the Use of wav2vec Representations for Multiclass Audio Segmentation},
author = {Pablo Gimeno and Alfonso Ortega and Antonio Miguel and Eduardo Lleida},
doi = {10.21437/IberSPEECH.2022-12},
year = {2022},
date = {2022-11-14},
urldate = {2022-11-14},
booktitle = {Proceedings of XII Jornadas en Tecnología del Habla and VIII Iberian SLTech (Iberspeech)},
pages = {56--60},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Pastor, Miguel; Ribas, Dayana; Ortega, Alfonso; Miguel, Antonio; Lleida, Eduardo
Cross-Corpus Speech Emotion Recognition with HuBERT Self-Supervised Representation Conferencia
Proceedings of XII Jornadas en Tecnología del Habla and VIII Iberian SLTech (Iberspeech), 2022.
@conference{Pastor2022,
title = {Cross-Corpus Speech Emotion Recognition with HuBERT Self-Supervised Representation},
author = {Miguel Pastor and Dayana Ribas and Alfonso Ortega and Antonio Miguel and Eduardo Lleida},
doi = {10.21437/IberSPEECH.2022-16},
year = {2022},
date = {2022-11-14},
urldate = {2022-11-14},
booktitle = {Proceedings of XII Jornadas en Tecnología del Habla and VIII Iberian SLTech (Iberspeech)},
pages = {76--80},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}