Embedded Files
Mercoledì 21 Gennaio 2026 / Wednesday 21 January 2026
Sala Malliani / Malliani hall
Università degli Studi di Milano / University of Milan
Via Festa del Perdono 7, Milano
La partecipazione agli eventi satellite è gratuita previa iscrizione al seguente link
Participation in the satellite events is free of charge, but you need to register at the following link
Programma
Programma
h. 11:00 - 13:00
h. 11:00 - 13:00
Deep fake audio: le nuove sfide della fonetica forense
(organizzato da Sonia Cenceschi & Chiara Meluzzi) - Tavola rotonda
Coordina Alessandro Trivilini
Intervengono:
Gerard Bailly
Sonia Cenceschi
Francesco Roberto Dani
Massimo Iuliani
Costanza Matteuzzi
Chiara Meluzzi
Elisa Pellegrino
Program
Program
h. 11:00 AM - 1:00 PM
h. 11:00 AM - 1:00 PM
Deep fake audio: the new challenges of forensic phonetics
(organized by Sonia Cenceschi & Chiara Meluzzi) - Round table
Coordinated by Alessandro Trivilini
Participants:
Gerard Bailly
Sonia Cenceschi
Francesco Roberto Dani
Massimo Iuliani
Costanza Matteuzzi
Chiara Meluzzi
Elisa Pellegrino
h. 14:30 - 18:30
h. 14:30 - 18:30
Recent developments in speech technologies. The Italian perspective in research and industry
(organizzato da Francesco Cutugno)
h. 14:30 - 14:45 Saluti istituzionali
- Presidente dell'AISV, Antonio Romano;
- Chiara Meluzzi.
h. 14:45 - 15:00 Phoné: Fundational models for Italian speech processing — Francesco Cutugno
h. 15:00 - 16:00 Invited speaker: Post hoc versus ad hoc control of Text-To-Speech synthesis — Gérard Bailly, Discussant Enrico Zovato
h. 16:00 - 16:20 Coffee break
Sessione di reportistica (modera Alessandro Vietti)
h. 16:20 - 16:40 Linguistic variability and resources in speech recognition — Loredana Schettino
h. 16:40 - 17:00 Phoné: Data resource report — Teresa Cimmino ed Emilia Tanda
h. 17:00 - 17:20 Phoné: ASR benchmarking — Gianpaolo Coro
h. 17:20 - 17:40 Multilingual speech technologies — Alessio Brutti (FBK)
Incontro con le aziende (modera Antonio Romano)
h. 17:40 - 17:55 Velvetspeech: The first Italian speech LLM — Leonardo Badino (Almawave)
h. 17:55 - 18:10 From accuracy to usability: New trends on ASR applications — Maria Palmerini (Cedat85)
h. 18:10 - 18:25 Speech technologies: A market perspective — Edoardo Barba (Principled Intelligence)
h. 18:25 Chiusura dei lavori
h. 2:30 - 6:30 PM
h. 2:30 - 6:30 PM
Recent developments in speech technologies. The Italian perspective in research and industry
(organized by Francesco Cutugno)
h. 2:30 - 2:45 PM Institutional greetings
- President AISV Committee, Antonio Romano;
- Chiara Meluzzi.
h. 2:45 - 3:00 PM Phoné: Fundational models for Italian speech processing — Francesco Cutugno
h. 3:00 - 4:00 PM Invited speaker: Post hoc versus ad hoc control of Text-To-Speech synthesis — Gérard Bailly, Discussant Enrico Zovato
h. 4:00 - 4:20 PM Coffee break
Reporting session (moderated by Alessandro Vietti)
h. 4:20 - 4:40 PM Linguistic variability and resources in speech recognition — Loredana Schettino
h. 4:40 - 5:00 PM Phoné: Data resource report — Teresa Cimmino and Emilia Tanda
h. 5:00 - 5:20 PM Phoné: ASR benchmarking — Gianpaolo Coro
h. 5:20 - 5:40 PM Multilingual speech technologies — Alessio Brutti (FBK)
Meeting with companies (moderated by Antonio Romano)
h. 5:40 - 5:55 PM Velvetspeech: The first Italian speech LLM — Leonardo Badino (Almawave)
h. 5:55 - 6:10 PM From accuracy to usability: New trends on ASR applications — Maria Palmerini (Cedat85)
h. 6:10 - 6:25 PM Speech technologies: A market perspective — Edoardo Barba (Principled Intelligence)
h. 6:25 PM Closure of proceedings for Satellite events
Aziende sponsor per gli eventi satelliti /Sponsor companies for the satellite event
Istituzioni organizzatrici per gli eventi satelliti / Organizing institutions for the satellite events
Page updated
Google Sites
Report abuse