Explainability in music deep learning models
Organisatsiooni nimi
Computational music analysis and recommendation
Kokkuvõte
Recently, autoregressive language models (transformers) have become SOTA in speech and music domain as well by using tricks to diminish the size of sequence while keeping a large receptive field. We would benefit from understanding what is the musical meaning behind learned tokens.
Lõputöö kaitsmise aasta
2022-2023
Juhendaja
Anna Aljanaki
Suhtlemiskeel(ed)
eesti keel, inglise keel
Nõuded kandideerijale
Tase
Magister
Märksõnad
Kandideerimise kontakt
Nimi
Anna Aljanaki
Tel
E-mail