Ti trovi qui: Home » People

Giovanni Morrone

Giovannii

 

Role:

PhD Student

Office:

Department of Engineering "Enzo Ferrari"
Via Pietro Vivarelli,10 - 41125, Modena, Italy
MO-27-01-a20 - 1st floor, MO 27 Building

Phone:

+39 059 2056314

Email:

giovanni.morrone@unimore.it

Supervisor: Prof. Sonia Bergamaschi
Co-Supervisor: Dr. Leonardo Badino (PerVoice)

 

Google Schoolar   linkedin-icon

Summary

I'm a PhD student in Industrial and Environmental Engineering (curriculum Industry 4.0) from November 2017. My main research activity concerns Machine/Deep Learning for Spoken Language Processing (Audio-Visual Speech Recognition/Enhancement/Separation). In particular I focus on very challenging environments where multiple speakers are talking at the same time (i.e. Cocktail Party scenario).
I did an industrial research internship at PerVoice (Trento) last year (September-December 2019) working on Automatic Speech Recognition in noisy environments.
I'm currently doing a research internship at CASPR (Aalborg University, Denmark). At CASPR I am working on audio-visual speech inpainting, i.e. reconstruction of missing parts of a speech signal using audio and visual information.
If you are interested in my research work check out my demo presentation at European Researchers' Night (link).

 

Teaching activities

  • Teaching tutor of "Foundations of Computer Science" (BSc Degree in Electronic Engineering - Unimore) [until September 2019]
  • Teaching assistant of "Database Systems" (BSc Degree in Computer Engineering)

 

Publications

  • Giovanni Morrone, Luca Pasa, Vadim Tikhanoff, Sonia Bergamaschi, Luciano Fadiga, Leonardo Badino, "Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments", 44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019), Brighton, United Kingdom, May 12-17, 2019. [project page][paper][code]
  • Luca Pasa, Giovanni Morrone, Leonardo Badino, "An Analysis of Speech Enhancement and Recognition Losses in Limited Resources Multi-talker Single Channel Audio-Visual ASR", 45th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), Barcelona, Spain, May 4-8, 2020. [paper]
  • Ander Arriandiaga, Giovanni Morrone, Luca Pasa, Leonardo Badino, Chiara Bartolozzi, "Audio-Visual Target Speaker Extraction on Multi-Talker Environment using Event-Driven Cameras". (submitted) [paper]

Categorie: Members