Talks on Automatic Analysis of Depressive Disorders and Communication Support to People with Speech Disorders

17 gennaio 2019
Versione stampabile

Time: 12pm-1pm
Venue:  via Sommarive 5 - Polo Ferrari 1 (Povo) - Ofek room

Speakers

  • Prof. Eduardo LLeida - University of Zaragoza
  • Prof. Alfonso Ortega - University of Zaragoza

Abstract

Assessment and Analysis of Major Depressive Disorder Based on Speech 

Major depressive disorder (MDD) affects around 7% of the adult population in Europe every year. Depression can be associated with premature mortality, risk of cardiovascular morbidity and mortality, accelerated atherosclerosis and early cardiovascular disease, etc. It is of utmost importance to early diagnose and monitor major depressive disorders and its evolution in order to allow an early and personalized treatment, improving patient’s health and quality of life.  

Nowadays, diagnosis of depression relies almost exclusively upon self-report using rating scales, questionnaires or interviews. No objective measurements exist in order to monitor patients, allowing the early diagnosis and follow-up of the disease. 

Recently, several markers or risk factors for depression have been investigated and proposed. The use of physiological signals is a noninvasive way for providing objective clues to assess and monitor depression. Speech (along with other physiological signals such as heart rate variability) are easy to acquire and therefore candidates to be used as markers to early diagnose and monitor MDD.

Research on the relation between speech and depression can be extensively found in the literature. In this talk, we will provide a brief insight into the different approaches that have been followed to diagnose, assess or monitor depression based on prosodic, articulatory or acoustic analysis of speech. In addition to that, we will describe the ongoing research that is being conducted in Zaragoza in this area.

Augmentative and Alternative Communication for People with Speech Disorders: Living with Pictograms.

Many people suffer from language disorders that affect their communicative capabilities. Augmentative and Alternative Communication (AAC) encompasses all sort of communication methods that supplement and ease, or even replace, spoken and/or written language. AAC devices assist communication and learning process through graphical representation of common words. Graphic symbols range from very simple systems based on drawings or photographs to progressively more complex systems such as pictographic systems or traditional spelling (letters, words and phrases). In this talk, we present the ARASAAC iniciative (Aragonese Portal of Augmentative and Alternative Communication) and some of the on-going projects we are collaborating on using pictograms to improve the communication skills of people with speech and language disorders.

About the speakers

Prof. Eduardo Lleida received the degree in telecommunication engineering and the Ph.D. degree from the Universitat Politècnica de Catalunya (UPC), Spain, in 1985 and 1990, respectively. From 1989 to 1990 he worked as assistant professor and from 1991 to 1993, he worked as associated professor in the Department of Signal Theory and Communications at the Universitat Politècnica de Catalunya, Spain. From February 1995 to January 1996, he was with AT&T Bell Laboratories, Murray Hill, NJ as a consultant in Speech Recognition.Currently, he is a full professor of Signal Theory and Communications in the Department of Electronic Engineering and Communications at the University of Zaragoza (Spain), and 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 as PI more than 50 speech-related projects, being inventor in 6 worldwide patents, and co-authored 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. He has been the organizer of the IV National Conference on Speech Technologies in 2006, the V Spanish Biometric People Recognition Conference in 2010 and co-organizer of the Speaker and Language Recognition International Workshop, Odyssey 2016.

Prof. Alfonso Ortega received the Telecommunications Engineer degree in 2000 and the PhD degree from the University of Zaragoza in 2005, with extraordinary doctorate Award and Telefonica Chair Award. He is author of more than 100 papers published in international journals or conference proceedings. He has participated in more than 50 research projects, both as a collaborating researcher and as principal investigator, half of them belong to competitive programs, both European and national (FP6, FP7, FEDER, CICYT, CENIT, PROFIT, AVANZA ...). He was coordinator since 2010 until 2017 of the Spanish Thematic Network in Speech Technologies (RTTH), which brings together the main Spanish research groups in the field. In 2006, he was visiting researcher at the University of Texas at Dallas (USA) and he have participated in mobility experiences such as invited courses or intensive Erasmus programs. He has been involved in more than 30 transfer of technology contracts with different companies being inventor in four international patents. He has participated in the organization of six conferences, 4 of them of international scope. Dr. Ortega is presently Associate Professor in the Department of Electronic Engineering and Communications at the University of Zaragoza

Contact person: Prof. giuseppe.riccardi [at] unitn.it (Giuseppe Riccardi)