We invite our LISTEN partners to an ADASP meeting which will be held in two parts:

  • Presentation of state-of-the-art/work of two PhD students (10 minutes each + 5 minutes of questions)
  • Presentation of done work of one PostDoc student (20 minutes + 10 minutes of questions)

Programme of PhD presentations:

Elio GRUTTADAURIA, “State of the art of Speaker Diarization and research directions in joint modeling of speech-related tasks”

 

 

 

 

 

Manvi AGARWAL, “Structural Information for Positional Encoding in Transformers for Music Generation”








Programme of PostDoc presentation:

Changhong WANG, “Scattering Transform for Audio Classification”