Papers of the day   All papers

The Bach Doodle: approachable music composition with machine learning at scale

Comments

Anna Huang: Remember the #BachDoodle? We’re excited to release paper on Behind-the-Scenes design, #ML, scaling it up, and dataset of 21.6M melodies from around the world! 📜 http://arxiv.org/abs/1907.06637 w/ @fjord41 @ada_rob @notwaldorf @bengiswex Leon Hong @jaxcooo https://t.co/sHvu2hLIrG

5 replies, 411 likes


Douglas Eck: Amazing paper and data on the Bach Doodle by @huangcza, @fjord41, @ada_rob, @notwaldorf, @bengiswex and @jaxcooo. 21.6 Megabachs of melodies.

0 replies, 34 likes


Tero Parviainen: That's a lot of music generated: "In three days, people spent 350 years worth of time playing with the Bach Doodle, and Coconet received more than 55 million queries."

2 replies, 25 likes


Miles Brundage: "The Bach Doodle: Approachable music composition with machine learning at scale," @huangcza et al.: https://arxiv.org/abs/1907.06637

0 replies, 22 likes


arxiv: The Bach Doodle: Approachable music composition with machine learning at scale. http://arxiv.org/abs/1907.06637 https://t.co/mjCSPPcwJj

0 replies, 22 likes


Joseph O'Brien Antognini: Google AI resident Anna Huang @huangcza has a really cool paper detailing the ML behind the Bach Google doodle that appeared back in March! They're also releasing the dataset of 20 million melodies that users composed. https://arxiv.org/abs/1907.06637

1 replies, 6 likes


Evan Tobias: How absolutely fantastic is this?!! Check out this paper & get inspired to think about #musiced more broadly - consider connections among music & #CS #STEAM #AI music analysis aural skills & any number of other possibilities #mused

0 replies, 5 likes


youngmoo: So cool! Enabling music composition on a massive scale through the Bach Google Doodle and Tensorflow.js. Can’t wait to read this paper! #ISMIR1019 #STEAMedu

0 replies, 3 likes


Content

Found on Jul 18 2019 at https://arxiv.org/pdf/1907.06637.pdf

PDF content of a computer science paper: The Bach Doodle: approachable music composition with machine learning at scale