Affective computing in the context of music therapy: a systematic review

Music therapy is an effective tool to slow down the progress of dementia since interaction with music may evoke emotions that stimulates brain areas responsible for memory. This most successful when therapists provide adequate and personalized stimuli each patient. personalization often hard. Thus, Artificial Intelligence (AI) methods help in this task. paper brings a systematic review literature field affective computing context therapy. We particularly aim assess AI perform automatic emotion recognition applied Human-Machine Musical Interfaces (HMMI). To review, we conducted search five main scientific databases on fields intelligent computing, engineering, medicine. all papers released from 2016 2020, whose metadata, title or abstract contains terms defined string. The protocol resulted inclusion 144 works 290 publications returned search. Through state-of-the-art, it was possible list current challenges emotions. It also realize potential build non-invasive assistive solutions based human-machine musical interfaces, as well artificial intelligence techniques use multimodality data. machine learning different data sources can be important approach optimize clinical goals achieved through