BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20251026T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.30056.field_data.0@www.u-gov-ricerca.uniroma1.it
DTSTAMP:20260404T233230Z
CREATED:20260115T193342Z
DESCRIPTION:AbstractWe live in an era when text-based language models are h
 aving a transformative impact on our societies. However\, written language
  is a relatively recent form of human communication if compared to spoken 
 language. Although tightly related\, the two differ in many ways. In this 
 talk\, I will go through some of our work in modelling spoken language wit
 h different but related goals. On the one hand\, we worked at improving te
 chnology such as automatic speech recognition and pronunciation assessment
  in specific conditions\, involving\, for example\, dialectal and age-rela
 ted variability. On the other hand\, we explored learning strategies that 
 are more comparable with human learning. This both in the hope to shed som
 e light on human language acquisition and to get inspiration for more effi
 cient machine learning methods. The key ingredients are explainability\, m
 ultimodality\, embodiment and active learning.BioGiampiero Salvi is Full P
 rofessor at the Department of Electronic Systems at the Norwegian Universi
 ty of Science and Technology (NTNU)\, Trondheim\, Norway. Earlier he was A
 ssociate Professor at KTH Royal Institute of Technology\, Department of El
 ectrical Engineering and Computer Science\, Stockholm\, Sweden. Prof. Salv
 i received the MSc degree in Electronic Engineering from Università la Sap
 ienza\, Rome\, Italy and the PhD degree in Computer Science from KTH. He w
 as a post-doctoral fellow at the Institute of Systems and Robotics\, Lisbo
 n\, Portugal. He was a co-founder of the company SynFace AB\, active betwe
 en 2006 and 2016. His main interests are machine learning\, speech technol
 ogy\, and cognitive systems.More info: https://www.ntnu.edu/employees/giam
 piero.salvi 
DTSTART;TZID=Europe/Paris:20260121T140000
DTEND;TZID=Europe/Paris:20260121T140000
LAST-MODIFIED:20260326T110808Z
LOCATION:Aula Magna
SUMMARY:On Modelling Spoken Language - Giampiero Salvi
URL;TYPE=URI:http://www.u-gov-ricerca.uniroma1.it/node/30056
END:VEVENT
END:VCALENDAR