bookmark_border

Google Brain Music Generation with Doug Eck

Software Engineering Daily,

Originally posted on Software Engineering Daily

Most popular music today uses a computer as the central instrument. A single musician is often selecting the instruments, programming the drum loops, composing the melodies, and mixing the track to get the right overall atmosphere.

With so much work to do on each song, popular musicians need to simplify–the result is that pop music today consists of simple melodies without much chord progression.

Magenta is a project out of Google Brain to design algorithms that learn how to generate art and music. One goal of Magenta is to advance the state of the art in machine intelligence for music and art generation. Another goal is to build a community of artists, coders, and machine learning researchers who can collaborate.

Engineers today are happy to outsource server management to a cloud service provider. Similarly, a musician can use Magenta for creation of a melody, so she can focus on other aspects of a song, such as instrumentation.

Doug Eck is a research scientist at Google. In today’s episode, we explore the Magenta project and the future of music.

Software Engineering Daily is having our third Meetup, Wednesday May 3rd at Galvanize in San Francisco. The theme of this Meetup is Fraud and Risk in Software. We will have great food, engaging speakers, and a friendly, intellectual atmosphere. To find out more, go to softwareengineeringdaily.com/meetup. We would love to get your feedback on Software Engineering Daily. Please fill out the listener survey, available on softwareengineeringdaily.com/survey.

Transcript

Transcript provided by We Edit Podcasts. Software Engineering Daily listeners can go to weeditpodcasts.com/sed to get 20% off the first two months of audio editing and transcription services. Thanks to We Edit Podcasts for partnering with SE Daily. Please click here to download this show’s transcript.

Sponsors


Deep learning promises to dramatically improve how our world works. To make deep learning easier and faster, we need new kinds of hardware and software–which is why Intel acquired Nervana Systems, a platform for deep learning. Intel Nervana is hiring engineers to help develop a full stack for AI, from chip design to software frameworks. Go to softwareengineeringdaily.com/intel to apply for a job at Intel Nervana. If you know don’t know much about the company, check out the interviews I have conducted with engineers from the company. You can find these at softwareengineeringdaily.com/intel.


Catch bugs before your users do with full-stack error monitoring and analytics for developers by Rollbar. With Rollbar’s error monitoring, you get the full stack trace, context, and user data to help you find and fix impactful errors super fast. You can integrate Rollbar into your existing workflow. Send error alerts to Slack or Hipchat. Or, automatically create new issues in JIRA, Pivotal Tracker, or Trello. Adding any of the Rollbar SDKs is as simple as a single command. Start tracking production errors in minutes. One cool feature is that GitHub repos can be deep linked directly to your stack traces in Rollbar. Go to rollbar.com/SEDaily, signup, and get the Bootstrap Plan free. Used by developers at companies like Heroku, Twilio, Kayak, Zendesk, Twitch, and more. To check out Rollbar, go to rollbar.com/SEDaily, signup, and get the Bootstrap Plan free.


Do you want the flexibility of a non-relational key value store together with the query capabilities of SQL? Take a look at c-treeACE by FairCom. c-treeACE is a non-relational key-value store that offers ACID transactions complemented by a full SQL engine. c-treeACE offers simultaneous access to the data through non-relational and relational APIs. Companies use c-treeACE to process ACID transactions through non-relational APIs for extreme performance while using the SQL APIs to connect third-party apps or query the data for reports or business intelligence. c-treeACE is platform- and hardware-agnostic, and is capable of being embedded, deployed on premises, or in the cloud. Software Engineering Daily listeners can download an evaluation version of c-treeACE for free at softwareengineering.com/faircom.


tensorflow

About the Podcast