Google Magenta 프로젝트

* 공식 페이지

https://research.google/teams/brain/magenta/

Magenta – Google Research

Magenta is an open source research project exploring the role of machine learning as a tool in the creative process.

Magenta는 창작 과정에서 도구로 기계 학습의 역할을 탐구하는 오픈 소스 연구 프로젝트입니다.

 

About the team

Magenta was started by researchers and engineers from the Google Brain team, but many others have contributed significantly to the project. We develop new deep learning and reinforcement learning algorithms for generating songs, images, drawings, and other materials. But it's also an exploration in building smart tools and interfaces that allow artists and musicians to extend their processes using these models. We use TensorFlow and release our models and tools in open source on our GitHub.

팀 소개
Magenta는 Google Brain 팀의 연구원과 엔지니어에 의해 시작되었지만 많은 사람들이이 프로젝트에 크게 기여했습니다. 노래, 이미지, 그림 및 기타 자료를 생성하기위한 새로운 딥 러닝 및 강화 학습 알고리즘을 개발합니다. 또한 예술가와 음악가가 이러한 모델을 사용하여 프로세스를 확장 할 수있는 스마트 도구와 인터페이스를 구축하는 데 대한 탐구이기도합니다. 우리는 TensorFlow를 사용하고 모델과 도구를 GitHub의 오픈 소스로 출시합니다.

 

https://magenta.tensorflow.org/

Magenta

 

 

 

* 프로젝트 소개

 

1. Magenta Studio

https://magenta.tensorflow.org/studio

Magenta Studio

Magenta Studio is a collection of music plugins built on Magenta’s open source tools and models. They use cutting-edge machine learning techniques for music generation.

These tools are available both as standalone applications and as plugins for Ableton Live. To find out more information, choose one of the links below:

Magenta Studio는 Magenta의 오픈 소스 도구 및 모델을 기반으로 구축 된 음악 플러그인 모음입니다. 그들은 음악 생성을 위해 최첨단 기계 학습 기술을 사용합니다.
이 도구는 독립형 응용 프로그램 및 Ableton Live 용 플러그인으로 사용할 수 있습니다. 자세한 정보를 보려면 아래 링크 중 하나를 선택하십시오.

 

The plugins and standalone applications do the same thing. The only difference is how you get MIDI in and out:
the Ableton Live plugin reads and writes clips from Ableton's Session View
the standalone application reads and writes files from your file system without requiring Ableton.
For example, here’s the Generate plugin in both the standalone and Ableton Live versions.

플러그인과 독립형 애플리케이션은 동일한 기능을 수행합니다. 유일한 차이점은 MIDI를 가져오고 나가는 방법입니다.
Ableton Live 플러그인은 Ableton의 세션보기에서 클립을 읽고 씁니다.
독립형 응용 프로그램은 Ableton을 요구하지 않고 파일 시스템에서 파일을 읽고 씁니다.
예를 들어 다음은 독립형 버전과 Ableton Live 버전의 생성 플러그인입니다.

 

https://magenta.tensorflow.org/studio/ableton-live

Magenta Studio - Ableton Live Plugin

 

https://magenta.tensorflow.org/studio/standalone

Magenta Studio - Standalone

 

 

 

 

 

2. Onsets and Frames

https://magenta.tensorflow.org/onsets-frames

Onsets and Frames: Dual-Objective Piano Transcription

 

3. MusicVAE

https://magenta.tensorflow.org/music-vae

MusicVAE: Creating a palette for musical scores with machine learning.

 

4. NSynth Super

https://nsynthsuper.withgoogle.com/

NSynth Super

 

 

 

* Some of our people

https://research.google/people/author39086/

Douglas Eck – Google Research

 

 

 

* 논문 목록

 

https://research.google/pubs/?collection=magenta