Report
Teaser, summary, work performed and final results
Periodic Reporting for period 3 - DoReMIR (Automatic music transcription of polyphonic audio)
Teaser
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...
Summary
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.
The solution will be piloted with 1000 users over 2 demonstrators in Sweden and Latvia.
The project’s objectives have been structured in 4 key areas that define clear, measurable key performance indicators or KPIs:
• Objective 1 (develop a cloud-based polyphonic music transcription solution based on new signal processing models): the project will develop an robust and accurate transcription engine able to process polyphonic music in the cloud and to provide the resulting data to any applications using its APIs.
• Objective 2 (develop new tools and applications supporting new pedagogical models for music schools): the project will implement a first application example (score transcription application for music composing and music teaching).
• Objective 3 (develop a vibrant ecosystem around the technology and models): the project will publish APIs and encourage third party developers to come up with their own innovative application ideas, based on the polyphonic music transcription engine.
• Objective 4 (successfully translate research results in scalable technology): the project will develop all the necessary foundations for a successful exploitation (product market launch) after the end of the project.
Work performed
This report covers the second third of the project Polyphoni-X-Score that started in May 2015.
Work has been intense and great deal has been achieved, however, the work has been more extensive than expected, in particular regarding WP2 and WP3 which has caused a delay in the progress and we are appr. six months behind schedule. We have, however, overcome the major issues and are confident we will be able to achieve the goals of the project.
Most efforts have been on:
- WP2 Development of the AMT (automatic Music Transcription Engine).
- WP3 Development of Cross plattform applications.
- WP4 Field trials & Evaluations.
Final results
We have made great achievements, including building a fully functioning prototype of a polyphonic audio-to-score transcription system, showing results going beyond state of the art for publically available applications. We have also developed a rich collaborative environment including end users and music pedagogic institutions that builds the foundation of technical development related to artistic and pedagogic needs.
We do not assess the potential impact differently from the Grant Agreement.
Please note that the results are confidential.
Website & more info
More info: http://www.x-score.eu.