Skip to main content

Automatic music transcription of polyphonic audio

Objective

DoReMIR Music Research has already launched several successful products for music analysis and composition and has a large user base of monophonic audio analysis worldwide. The project builds on and extends a product suite called ScoreCloud with the focus on easy creation and distribution of music notation. The ScoreCloud concept is technically built on mobile and desktop apps connected with a full cloud based back-end. The product enables users to notate music directly from performance: a Google Translate for Music!
The project will develop a low-cost, cloud-based, polyphonic audio transcription solution based on an interdisciplinary approach (musicology, acoustics, audio engineering, cognitive science and computing) and a user-driven design (agile iterative solution development with end-user participation in the context of music teaching and music composition).
In order to circumvent the limitations of current automated transcription methods, the project uses a novel approach to musical and music signal analysis, by modelling and using high-level musical knowledge (about stylistic conventions, music cognition, etc.) and machine learning techniques. In addition to finding better solutions to certain analysis problems, the resulting systems will also be able to communicate their results in musically meaningful, high-level terms.

Field of science

  • /humanities/arts/art history/musicology
  • /natural sciences/computer and information sciences/artificial intelligence/machine learning

Call for proposal

H2020-SMEINST-2-2014
See other projects for this call

Funding Scheme

SME-2 - SME instrument phase 2

Coordinator

DOREMIR MUSIC RESEARCH AB
Address
Tegnergatan 15
111 40 Stockholm
Sweden
Activity type
Private for-profit entities (excluding Higher or Secondary Education Establishments)
EU contribution
€ 2 086 262,50