AUDIAS logo Audio, Data Intelligence and Speech
EPS logo UAM logo

Senior Staff

Staff

Associated Staff

Postdoc Researchers

Research Assistants


Joaquin Gonzalez-Rodriguez [Email]
Photo

Joaquin Gonzalez-Rodriguez, Ph.D. (1999) in Electrical Engineering from Univ. Politecnica de Madrid (UPM), Spain, founded in early 2000s and co-led the ATVS Biometric Recognition Group up to october 2016, when ATVS splits his current activities in two groups. He now leads AUDIAS Research Group, devoted to Research and Development in the areas of Speech and Audio, Temporal Signals Processing (Sensor arrays, Financial series, etc.), Forensic Science and Data Intelligence. Since July 2011 he is a Full Professor in the Electronic and Communication Technologies Department at Universidad Autonoma de Madrid (UAM). He has led ATVS participations in multiple NIST Speaker and Language Recognition Evaluations since 2001, and he is since 2000 an invited member of the FSAAWG (Forensic Speech and Audio Analysis Working Group) in ENFSI (European Network of Forensic Science Institutes). In September 2008, he addressed a keynote plenary talk at Interspeech 2008 in Brisbane (Australia) entitled “Forensic Automatic Speaker Recognition: Fiction or Science?”. In March 2009 he received a Google Research Award for the project entitled “Exploiting prior knowledge for robust recognition and indexing of audio information sources”. During academic term 2010-2011, he was on sabbatical leave as Visiting Scholar at ICSI (International Computer Science Institute) in the University of California at Berkeley. Since 2012, he leads a long-term project on virtual scenarios of high-dimensional multivariate financial data for algorithmic trading, and fosters and coordinates the ATVS (now AUDIAS) series of Seminars (http://audias.ii.uam.es/listseminars.do). In 2017, he led AUDIAS participation in ASVspoof 2017 with an innovative audio fingerprinting approach to speaker verification anti spoofing. His research interests are focused on speaker and language characterization, financial series modeling, audio & music indexing, acoustics, and forensic science.

Doroteo Torre-Toledano [Email]
Photo

Doroteo Torre Toledano, received the M.S. degree in 1997, and the Ph.D. degree Electrical and Electronic Engineering in 2001, both from Universidad Politecnica de Madrid, Spain. He has been recipient of several academic awards, such as the First National Bachelor Award of Spain, the best academic record in Electrical and Electronic Engineering (of 448 students) and a Ph.D. Dissertation Award from the Spanish Association of Telecommunication Engineers. After his Ph.D., he joined M.I.T. as Postdoctoral Research Associate in the Spoken Language Systems Group (2001-2002), under the supervision of Profs. Victor Zue and Jim Glass. He has also experience working in the industry, in particular in the Speech Technology Division of Telefonica R&D, where he worked from 1994 to 2001 and also in 2003. His trajectory as professor in signal processing starts in 2004, when he joined Universidad Autonoma de Madrid, where he is currently Associate Professor. Prof. Toledano has over 20 years of experience in speech processing, over 100 scientific publications. He has participated in 6 EU research projects and in over 40 national projects (in 10 of them as principal investigator). He has participated in over 15 technological competitive evaluations (mainly NIST evaluations) and has organized three. He was General Co-Chair and main organizer of IberSPEECH 2012, and organizer and session chair of several other conferences. Prof. Toledano current research is focused on speech, speaker, language and pathology recognition, particularly based on deep learning approaches.

Daniel Ramos [Web] [Email]
Photo

Dr. Daniel Ramos finished his PhD in 2007 in Universidad Autonoma de Madrid (UAM), Spain. From 2011, he is an Associate Professor at the UAM. He is a member of the ATVS - Biometric Recognition Group and the UAM Research Institute of Forensic Science and Security (ICFS). During his career, he has visited several research laboratories and institutions around the world, including the Institute of Scientific Police at the University of Lausanne (Switzerland), the School of Mathematics at the University of Edinburgh (Scotland), the Electrical Engineering school at the University of Stellenbosch (South Africa), and more recently the Netherlands Forensic Institute, where he has co-organized a workshop on the scientific validation of evidence evaluation methods. His research interests are focused on forensic evaluation of the evidence using Bayesian techniques, validation of forensic evaluation methods, speaker and language recognition, biometric systems and, more generally, signal processing and pattern recognition. Dr. Ramos is actively involved in several projects focused on different aspects of forensic science, such as yearly R&D contracts with Spanish Guardia Civil, the EU FP7 Marie Curie Initial Training Network BBfor2 (Bayesian Biometrics for Forensics), or the Management Committee of the EU COST 1106 Action on Forensic Biometrics. He has received several distinctions and awards, highlighting the IBM Research Best Student Paper Award at the IEEE Odyssey 2006 Speaker and Language Recognition Workshop, and the Telecommunication Engineer Best PhD Thesis Award in 2007-2008 from the Official College of Spanish Telecommunication Engineers (Colegio Oficial de Ingenieros de Telecomunicacion, COIT). He is author of multiple publications in national and international journals and conferences. He has also participated in several international competitive evaluations of speaker and language recognition technology, such as NIST Speaker Recognition Evaluations since 2004, the Forensic Speaker Recognition Evaluation NFI/TNO 2003 and the NIST Language Recognition Evaluation since 2007. Dr. Ramos is regularly a member of scientific committees in different international conferences, and he is often invited to give talks in conferences and institutions.

Javier Franco-Pedroso [Email]
Photo

Javier Franco-Pedroso recieved the M.S. degree in telecommunication engineering from Universidad Politécnica de Madrid (UPM), Madrid, Spain, in 2011 and the Ph.D degree (cum laude) in computer science and telecommunication engineering from Universidad Autónoma de Madrid (UAM), Madrid, Spain, in 2016. Since 2004, he has been with the ATVS - Biometric recognition group, taking part in research projects from different topics: speaker and language recognition, speaker diarization, audio segmentation and time series analysis and synthesis. Dr. Franco-Pedroso recieved several distinctions, such as the M.S. Dissertation Award from the Official College of Spanish Telecommunication Engineers (Colegio Oficial de Ingenieros de Telecomunicacion, COIT) or the Finalist Certificate at the European Biometrics Research and Industry Award 2016.

Javier Gonzalez-Dominguez [Email]
Photo

Javier Gonzalez-Dominguez received his M.S. degree in Computer Science in 2005 from Universidad Autonoma de Madrid, Spain. In 2005 he joined Biometric Recognition Group - ATVS at Universidad Autonoma de Madrid (U.A.M) as a Ph. D. student. In 2007 he obtained the postgraduate Master in Computer Science and Electrical Engineering from U.A.M and received a FPI research fellowship from Spanish Ministerio de Educacion y Ciencia. His research interests are focused on robust speaker and language recognition. He has been recipient of several awards as the Microsoft Best student paper at SIG-IL 2009 conference and fellowships. Javier Gonzalez-Dominguez has actively participated and led several ATVS systems submitted to the NIST speaker and language evaluation recognition since 2006. During his Ph.D. pursuit he has been member of several research sites as SAIVT-QUT (2008, Brisbane, Australia), TNO (2009, Utrecht, The Netherlands) and Google Inc. Research (2010 New York, U.S.A).

Alicia Lozano-Diez [Email]
Photo

Alicia Lozano-Diez received the double degree in Computer Science and Mathematics from Universidad Autónoma de Madrid (UAM), Spain, in 2012, and the postgraduate Master in Research and Innovation in Information and Communications Technologies (I2-TIC) from the same University in 2013. Since 2012, she has been with the Audias research group at Universidad Autonoma de Madrid (previously ATVS group), where she is currently pursuing her PhD. Her research is focused on the use of deep neural networks (DNN) for the tasks of automatic language and speaker recognition. In 2015, she joint for a four month research internship the Speech group at Brno University of Technology (BUT, Brno, Czech Republic). In the 2016 summer, she interned at SRI International (STAR Lab, California, USA). During these two research internships, she worked with each of these leading research groups in the field, researching on the main topics of her PhD.

Ruben Zazo [Email]
Photo

Ruben Zazo received the MSc in Electrical Engineering in 2014 from Universidad Autonoma de Madrid achieving the best records of hiss class and the ASISA award to the best Academic Trajectory in Telecommunications Engineering. He is currently a M.S. Graduated Researcher pursuing the PhD degree with AUDIAS research group. In 2015 he interned at Google Inc. in their headquarters in Mountain View, California, where he joined the speech research team. Later in 2015 he was awarded with a FPI research fellowship from Universidad Autonoma de Madrid. In 2016 he interned at Johns Hopkins University under the supervision of Najim Dehak. Ruben is currently involved in Deep Neural Networks, Recurrent Neural Networks (LSTM), big data, and other state-of-the-art pattern recognition techniques. His interests are multi-disciplinary including Artificial Intelligence, Deep Learning, Patern Recognition, Robotics or Electronics.