Gracenote is a company founded in 1998 that provides music, video, and automotive metadata through web APIs and SDKs. Their services include music recognition for cloud services/apps, discovery/playlisting, and enhanced voice recognition for automobiles. They have over 300 employees across several offices and process billions of queries each year. They offer web APIs, mobile SDKs for iOS/Android, and desktop GNSDK for music identification and playlist generation.
This presentation is dedicated to different aspects of web audio playback instruments. The sample application mentioned can be found here:
https://jsfiddle.net/rost/efzabd36/
This presentation by Rostyslav Siryk (Senior Software Engineer, GlobalLogic) was delivered at Front-End Practice #1 on July 22, 2015 in Kharkiv.
The first hackathon was held in 1999, and had 10 developers. Nowadays, hackathons like TechCrunch Disrupt and PennApps draw over 1000 hackers. There are hackathons happening almost every day, in cities all over the world. The themes of these hackathons range from music, television, mobile development, security, civic hacking, education, tourism, and almost anything you can think of.
Gracenote has been participating in hackathons all over the world. This presentation talks about the growth of hackathons, and the involvement of our developer program and API evangelists. It was presented at The State of Music Discovery event in Tokyo, Japan, on Feb 18th, 2014 (http://www.gracenote.com/events/musicdiscovery_japan2014), on the week of the first Music Hack Day in Tokyo.
This presentation is dedicated to different aspects of web audio playback instruments. The sample application mentioned can be found here:
https://jsfiddle.net/rost/efzabd36/
This presentation by Rostyslav Siryk (Senior Software Engineer, GlobalLogic) was delivered at Front-End Practice #1 on July 22, 2015 in Kharkiv.
The first hackathon was held in 1999, and had 10 developers. Nowadays, hackathons like TechCrunch Disrupt and PennApps draw over 1000 hackers. There are hackathons happening almost every day, in cities all over the world. The themes of these hackathons range from music, television, mobile development, security, civic hacking, education, tourism, and almost anything you can think of.
Gracenote has been participating in hackathons all over the world. This presentation talks about the growth of hackathons, and the involvement of our developer program and API evangelists. It was presented at The State of Music Discovery event in Tokyo, Japan, on Feb 18th, 2014 (http://www.gracenote.com/events/musicdiscovery_japan2014), on the week of the first Music Hack Day in Tokyo.
Which city has better taste in music, Oakland, or San Francisco?
This hack, built in 24 hours at Hella Hack Oakland, uses the Twitter API and Gracenote metadata to analyze the genres and moods of music being shared on different music services (Pandora, Rdio, Soundtracking, Spotify), and creates an Rdio playlist of the songs being Tweeted.
What's a Hack? What's a Hackathon? And how do I survive, and better yet, succeed at a Hackathon?
This presentation is an introduction to hacking and hackathons (also known as hack days), and contains valuable tips for the novice and experienced hacker alike to make the most effective use of their time at a hackathon, and to prepare their hack and presentation to make the best impression on audiences and judges.
Machine Learning and Big Data for Music Discovery at SpotifyChing-Wei Chen
Spotify is the world’s largest on-demand music streaming company, with over 100 million active users who generate around 2TB of interaction data every day. With over 30 million songs to choose from, discovery and personalization play an essential role in helping users discover the best music for them. In this talk, given at the newly opened Galvanize space in NYC in March 2017, we’ll explain how Spotify uses Latent Space Models and Deep Learning to power features such as Discover Weekly and Release Radar.
Algorithmic Music Recommendations at SpotifyChris Johnson
In this presentation I introduce various Machine Learning methods that we utilize for music recommendations and discovery at Spotify. Specifically, I focus on Implicit Matrix Factorization for Collaborative Filtering, how to implement a small scale version using python, numpy, and scipy, as well as how to scale up to 20 Million users and 24 Million songs using Hadoop and Spark.
Interactive Recommender Systems with Netflix and SpotifyChris Johnson
Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction.
In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests.
The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems.
From Idea to Execution: Spotify's Discover WeeklyChris Johnson
Discover Weekly is a personalized mixtape of 30 highly personalized songs that's curated and delivered to Spotify's 75M active users every Monday. It's received high acclaim in the press and reached 1B streams within its first 10 weeks. In this slide deck we dive into the narrative of how Discover Weekly came to be, highlighting technical challenges, data driven development, and the Machine Learning models used to power our recommendations engine.
The Evolution of Spotify Home Architecture - Qcon 2019Karthik Murugesan
This talk will take the audience through the evolution of Spotify's architecture that serves recommendations (playlist, albums, etc) on the home tab. We'll discuss the tradeoffs of the different architectural decisions we made and how we went from batch pipelines to services to a combination of services and streaming pipelines.
In this MWC/ADC 2013 presentation Steve Robbins, Chief Architect for Nokia Music, explores the features of the Nokia Music Windows Phone API and shows you how to install and use the API. He then describes how to code with the API to quickly add music features to existing apps, and demonstrates how to get music content into your app.
For more information see www.developer.nokia.com/windowsphone and http://www.developer.nokia.com/Resources/Library/Lumia/#!nokia-music-apis.html.
Find out more about the developer features of Nokia Lumia smartphones in the Lumia App Labs: http://www.developer.nokia.com/Develop/Windows_Phone/Learn/
Presentation video here: https://www.youtube.com/watch?v=goUzHd7cTuA&feature=youtu.be
When we talk about the Science of Music, determining useful information about raw audio is a very non-trivial task. Spotify (and the Echonest) has done a lot of impressive work in deriving data from audio such as beat and bar detection, timbre encoding, pitch data, and more. Spotify has made all of this information available for the public to use -- now it's up to you to figure out what you'd like to do with it!
The Spotify Web API provides a wealth of information on nearly all music within the Spotify catalog. From the API, you can get information on artists, tracks, albums, as well as both low and high-level audio analysis information. This talk will discuss what information is available to the public, show some examples of how to find and use it, and give a crash course in accessing this data from a Python application.
A presentation of some of the security features and APIs in iPhone OS, allowing discussion of the threat model underlying Apple's chosen mitigation technology.
Going Platinum: How to Make a Hit API by Bill Doerrfeld, Nordic APIsNordic APIs
A presentation given by Bill Doerrfeld, Editor in Chief of Nordic APIs, at our 2024 Austin API Summit, March 12-13.
Session Description: As it turns out, making a hit API is a lot like making a hit music album. You have to find a niche, you need good naming, and you need quality content. Also, on the production side, design, style, experience, and collaboration all matter a lot. At the end of the day, both are products, requiring the right management tools, marketing know-how, and infrastructure to scale. In this SXSW-inspired opening keynote, I'll look into the parallels between the two endeavors, providing a fun and informative look into specific things API providers should be considering on their journey toward becoming API platform rockstars.
Which city has better taste in music, Oakland, or San Francisco?
This hack, built in 24 hours at Hella Hack Oakland, uses the Twitter API and Gracenote metadata to analyze the genres and moods of music being shared on different music services (Pandora, Rdio, Soundtracking, Spotify), and creates an Rdio playlist of the songs being Tweeted.
What's a Hack? What's a Hackathon? And how do I survive, and better yet, succeed at a Hackathon?
This presentation is an introduction to hacking and hackathons (also known as hack days), and contains valuable tips for the novice and experienced hacker alike to make the most effective use of their time at a hackathon, and to prepare their hack and presentation to make the best impression on audiences and judges.
Machine Learning and Big Data for Music Discovery at SpotifyChing-Wei Chen
Spotify is the world’s largest on-demand music streaming company, with over 100 million active users who generate around 2TB of interaction data every day. With over 30 million songs to choose from, discovery and personalization play an essential role in helping users discover the best music for them. In this talk, given at the newly opened Galvanize space in NYC in March 2017, we’ll explain how Spotify uses Latent Space Models and Deep Learning to power features such as Discover Weekly and Release Radar.
Algorithmic Music Recommendations at SpotifyChris Johnson
In this presentation I introduce various Machine Learning methods that we utilize for music recommendations and discovery at Spotify. Specifically, I focus on Implicit Matrix Factorization for Collaborative Filtering, how to implement a small scale version using python, numpy, and scipy, as well as how to scale up to 20 Million users and 24 Million songs using Hadoop and Spark.
Interactive Recommender Systems with Netflix and SpotifyChris Johnson
Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction.
In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests.
The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems.
From Idea to Execution: Spotify's Discover WeeklyChris Johnson
Discover Weekly is a personalized mixtape of 30 highly personalized songs that's curated and delivered to Spotify's 75M active users every Monday. It's received high acclaim in the press and reached 1B streams within its first 10 weeks. In this slide deck we dive into the narrative of how Discover Weekly came to be, highlighting technical challenges, data driven development, and the Machine Learning models used to power our recommendations engine.
The Evolution of Spotify Home Architecture - Qcon 2019Karthik Murugesan
This talk will take the audience through the evolution of Spotify's architecture that serves recommendations (playlist, albums, etc) on the home tab. We'll discuss the tradeoffs of the different architectural decisions we made and how we went from batch pipelines to services to a combination of services and streaming pipelines.
In this MWC/ADC 2013 presentation Steve Robbins, Chief Architect for Nokia Music, explores the features of the Nokia Music Windows Phone API and shows you how to install and use the API. He then describes how to code with the API to quickly add music features to existing apps, and demonstrates how to get music content into your app.
For more information see www.developer.nokia.com/windowsphone and http://www.developer.nokia.com/Resources/Library/Lumia/#!nokia-music-apis.html.
Find out more about the developer features of Nokia Lumia smartphones in the Lumia App Labs: http://www.developer.nokia.com/Develop/Windows_Phone/Learn/
Presentation video here: https://www.youtube.com/watch?v=goUzHd7cTuA&feature=youtu.be
When we talk about the Science of Music, determining useful information about raw audio is a very non-trivial task. Spotify (and the Echonest) has done a lot of impressive work in deriving data from audio such as beat and bar detection, timbre encoding, pitch data, and more. Spotify has made all of this information available for the public to use -- now it's up to you to figure out what you'd like to do with it!
The Spotify Web API provides a wealth of information on nearly all music within the Spotify catalog. From the API, you can get information on artists, tracks, albums, as well as both low and high-level audio analysis information. This talk will discuss what information is available to the public, show some examples of how to find and use it, and give a crash course in accessing this data from a Python application.
A presentation of some of the security features and APIs in iPhone OS, allowing discussion of the threat model underlying Apple's chosen mitigation technology.
Going Platinum: How to Make a Hit API by Bill Doerrfeld, Nordic APIsNordic APIs
A presentation given by Bill Doerrfeld, Editor in Chief of Nordic APIs, at our 2024 Austin API Summit, March 12-13.
Session Description: As it turns out, making a hit API is a lot like making a hit music album. You have to find a niche, you need good naming, and you need quality content. Also, on the production side, design, style, experience, and collaboration all matter a lot. At the end of the day, both are products, requiring the right management tools, marketing know-how, and infrastructure to scale. In this SXSW-inspired opening keynote, I'll look into the parallels between the two endeavors, providing a fun and informative look into specific things API providers should be considering on their journey toward becoming API platform rockstars.
How to broadcast a podcast live on Ustream with picture in picture, desktop, even a live chat stream. This is how I create the Live NosillaCast Podcast every Sunday night at 5pm Pacific Time at http://podfeet.com/live
Presented at FITC Toronto 2017
More info at http://fitc.ca/event/to17/
Presented by Jean-Philippe Côté, TangibleJS
Overview
If you own an electronic music instrument made in the last 3 decades, it most likely supports the MIDI protocol. What if we told you that it is now possible to interact with your beloved keytar, drum machine or MIDI software directly from your browser? You would go crazy, right? Well, prepare to do so…
With built-in support inside Chrome and Opera, upcoming support in Firefox and plugins for other platforms, this possibility is now a reality. This talk will introduce the audience to the Web MIDI API and to a library that will help you get the most out of it called WebMidi.js.
Web devs, man your synths!
Objective
Kickstart the development of web-based, MIDI-driven projects.
Target Audience
Web developers who want to make some noise and musicians paying bills doing front-end dev gigs
Assumed Audience Knowledge
Basic knowledge of the world’s top 4 languages: HTML, CSS, JavaScript and MIDI
Five Things Audience Members Will Learn
What the Web MIDI API is and what it can be used for
What the current support level for MIDI in browsers is
Why the Web MIDI API is too low-level for the average web developer and what can be done about it
How to send MIDI commands to MIDI devices and how to react to incoming MIDI events
How it sounds when a web developer transforms into an electronic musician
Gracenote API Walkthrough @ Music Hack Day SF ’13
1. API Walkthrough @ MusicHackDay San Francisco '13
Ching-Wei Chen (@cweichen)
2. Gracenote
●
Founded in 1998
●
Offices in the U.S. (SF Bay Area), Japan, Korea,
Taiwan and Germany
●
300+ employees
3. Business Verticals
Music Video Automotive
Music recognition for Cloud Interactive Program Guide – TV Music recognition, playlisting and
services and Apps Listings metadata clean-up
Audio and video recognition for Cover Art and Artist Images
Discovery and playlisting Second screen Apps
Linking Enhanced voice recognition
Smart recommendations
5. Business Verticals
Music Video Automotive
Music recognition for Cloud Interactive Program Guide – TV Music recognition, playlisting and
services and Apps Listings metadata clean-up
Audio and video recognition for Cover Art and Artist Images
Discovery and playlisting Second screen Apps
Linking Enhanced voice recognition
Smart recommendations
6. Business Verticals
Music Video Automotive
Music recognition for Cloud Interactive Program Guide – TV Music recognition, playlisting and
services and Apps Listings metadata clean-up
Audio and video recognition for Cover Art and Artist Images
Discovery and playlisting Second screen Apps
Linking Enhanced voice recognition
Smart recommendations
9. Web API
●
Delivers a rich set of music metadata (XML)
●
Text Search Query
●
Returns
– Artist: genres, origin, decades, images, bio, …
– Album: cover art, track listing, …
– Track: tempo, mood, …
10. Web API
●
Wrappers
●
Python
https://github.com/cweichen/pygn
●
PHP
https://github.com/richadams/php-gracenote
●
Java
https://github.com/richadams/java-gracenote
11. Web API
●
Wrappers
●
Python
https://github.com/cweichen/pygn
●
PHP
https://github.com/richadams/php-gracenote
●
Java
https://github.com/richadams/java-gracenote
12. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
13. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
14. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
15. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
Medium Tempo, Heavy Brooding song
by a Swedish Defiant Punk band from the 1990's
16. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
Medium Tempo, Heavy Brooding song
by a Swedish Defiant Punk band from the 1990's
17. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
Medium Tempo, Heavy Brooding song
by a Swedish Defiant Punk band from the 1990's
18. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
Medium Tempo, Heavy Brooding song
by a Swedish Defiant Punk band from the 1990's
19. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
Medium Tempo, Heavy Brooding song
by a Swedish Defiant Punk band from the 1990's
20. Web API
import pygn # Get it at https://github.com/cweichen/pygn
clientID = 'XXXXXX-XXXXXXXXXXXXXXXXXX'
userID = pygn.register(clientID) # only call it once!
metadata = pygn.searchTrack(clientID, userID,
'Backyard Babies',
'',
'Minus Celsius')
Medium Tempo, Heavy Brooding song
by a Swedish Defiant Punk band from the 1990's
22. Mobile Client
●
iOS & Android SDK
●
Provides all Web API functionality PLUS
●
Library identification (audio fingerprinting)
●
Streaming "Over The Air" identification
●
Sample iOS & Android application in SDK
28. Prizes
●
Best Gracenote Hack: 2 passes to Outside Lands
Music Festival
●
Favorite Hack: Beats by Dre Pill Portable Wireless
Speakers
29. Ideas
●
Music Taste Visualizer use Facebook likes or Last.fm scrobbles +
Gracenote metadata to create a visualization of a user’s music collection
and tastes, or his/her friend’s music tastes
●
Music ID use Gracenote fingerprinting to ID songs on mobile device and
do ???
●
Mood-based music exploration
●
Mood Lighting Change the ambient of a room, according to the
mood/tempo of the song