Simulating music with associative self-organizing maps

Miriam Buonamente, Haris Dindo, Antonio Chella, Magnus Johnsson

Forskningsoutput: TidskriftsbidragArtikelPeer review

1 Citeringar (Scopus)

Sammanfattning

We present an architecture able to recognise pitches and to internally simulate likely continuations of partially heard melodies. Our architecture consists of a novel version of the Associative Self-Organizing Map (A-SOM) with generalized ancillary connections. We tested the performance of our architecture with melodies from a publicly available database containing 370 Bach chorale melodies. The results showed that the architecture could learn to represent and perfectly simulate the remaining 20% of three different interrupted melodies when using a context length of 8 centres of activity in the A-SOM. These promising and encouraging results show that our architecture offers something more than what has previously been proposed in the literature. Thanks to the inherent properties of the A-SOM, our architecture does not predict the most likely next pitch only, but rather continues to elicit activity patterns corresponding to the remaining parts of interrupted melodies by internal simulation.

OriginalspråkEngelska
Sidor (från-till)135-140
Antal sidor6
TidskriftBiologically Inspired Cognitive Architectures
Volym25
DOI
StatusPublicerad - 2018-aug.
Externt publiceradJa

Fingeravtryck

Fördjupa i forskningsämnen för ”Simulating music with associative self-organizing maps”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här