Following the posts in which I’ve used Clarifai’s deep leaning API to tag, classify and then automatically generate album covers, here’s a quick experiment to analyze… Continued reading Tagging YouTube’s music videos with Clarifai deep learning
It’s been out for a few weeks, but I haven’t blogged about it, so here it is: My e-book #MusicTech is now available on leanpub.… Continued reading #MusicTech: An e-book on data science, analytics, recommender systems, and music discovery
Two weeks ago, I wrote about how I used Clarifai‘s deep learning image recognition API and Google Prediction to identify an artist genre based on their album cover. But what… Continued reading Automatically generate album covers with deep learning
With the recent news of image recognition start-up Clarifai raising $10M, I decided to experiment with their Web API. While Deep Learning (the core of their… Continued reading Identifying music genres from Spotify album covers using Clarifai’s deep learning API and Google Prediction
With CES starting tomorrow, I though it would be a good time to reflect on the future of music streaming, and what’s needed to own the space. Not… Continued reading Context: The future of music streaming and personalisation?
24’s idea is simple: Identify the top-24 tracks of the top-24 genres played via YouTube during the last 24 hours on Twitter. It’s based on the… Continued reading 24 hours, 24 genres, 24 tracks: Discover YouTube music trends via Twitter
Following my journey with Google Cloud, in particular BigQuery, I’m building a pipeline which mines Tweets containing YouTube videos, and maps those videos to Freebase in order to run various discovery / recommendations… Continued reading Sharing YouTube music on Twitter: Analytics using Freebase and BigQuery
YouTube Music Key, YouTube’s music subscription service, is about to go live – and I’m obviously very excited about this. As YouTube is one of the top… Continued reading YouTube Music Key: My hopes for music discovery and personalisation
A few days ago, Warner Music acquired Playlists.net, and as Techcrunch pointed out, one reason can be be its data, and the related insights. But, what can we learn… Continued reading Insights from 500,000 Deezer playlists using Google’s BigQuery
If you log-in to Deezer, Spotify, YouTube, etc. to listen to a particular artist, you can simply pick their top-tracks. Yet, while they’re the most popular,… Continued reading How mood and tempo can influence artist discovery?