From Paris to Bordeaux, an interview with Deezer’s CTO

On this (special) occasion, the…

Women’s Voices — A Brand Story

Part. 1: Women’s Voices — A Product Story Part. 2: Women’s Voices — A Brand Story Part. 3: Women’s Voices — A Data Story Part. 4: Women’s Voices — A…

Private libraries in Android — why you should consider it.

Part 1: Private libraries in Android — why you should consider it Part 2: Private libraries in Android — how to manage them Libraries are one of the foundations of Android development. Think about all dependencies in your Android projects…

Using a “go links” service in your organization

When I joined Deezer three years ago, the onboarding process (called DeezCover) was undergoing a complete redesign, so mine was relatively brief. I struggled to find my way around the company’s organization and documentation as I stepped into my new job. Of course, there was an internal Wiki, but you…

Detecting explicit content in songs

We’ve done some research about how to automatically detect explicit content in songs using only the music itself, and no additional metadata. Since it’s a sensitive and subjective issue, we did not want to use a black-box model, but rather build a modular system whose decisions can be traced back…

Akka as a bridge between REST and Kafka

Source: sciencing.com At Deezer, we love to play different chords, and to play with different technologies. Here we will present a solution to the problem of receiving millions of messages per day from a REST endpoint, processing them and pushing them back to Kafka. Inspired by The Reactive…

Throwback to Deezer ConTEST: the first hackathon for Product and QA

Deezer has a long tradition of hosting and organizing tech events such as internal or external hackathons, meetups, and more. Our motivation is to offer our people learning experiences by connecting them to external communities. Deezer ConTest was about encouraging our QA and…

Content Import en PHP chez Deezer

Deezer is a partner of the PHP Tour 2017 and several of our developers…

Merging like it’s 2099

Anyone who has worked with a big team on a big project has experienced merge conflicts at least once. Presentation of AutoMergeTool at AndroidMakers 2017 If you have never seen a list of ‘CONFLICT’ lines when rebasing or merging…

Releasing Spleeter: Deezer R&D source separation engine

In a nutshell We are releasing Spleeter to help the research community in Music Information Retrieval (MIR) leverage the power of a state-of-the-art source separation algorithm. It comes in the form of a Python Library based on Tensorflow, with pretrained models for 2, 4 and 5 stems separation. Spleeter will be presented…

Visualize your music DNA with Data

At Deezer, we take the world of music and make it personal. That’s why we designed Flow, your personal soundtrack, and a dynamic home page to help you find your perfect tracks in no time. But does personal content only revolve around music recommendation? Of course not! This article will…

What’s Right with Errors

You’re enjoying your app when suddenly an error message pops up, reading “Error: Something went wrong” Or you’re developing a new feature and attempting to interact with this outdated API that just returns NO when you call [Obscure.sharedManager doYourMagic] … And you’re frustrated!

1001 ways to code your projects, 1 way to meet your needs

Have you ever noticed that there are about 1001 ways to do something, especially in software development? As I tell every developer who joins my team, especially interns or junior devs, no one knows everything and every solution should be considered. I was recently confronted with 1001 ways of doing…

What The Bug? Our method to detect outliers

Who are we? We are the Data-Analytics team. Insights, numbers, dashboards… we provide data to our company. The goal? Help business and product teams in designing music and digital experiences that will be the best they can be for our users. Why do we need to detect outliers? As a tech data team, we rely on different KPIs. We check…

Improving your ingestion performance using the multidisciplinary approach

When it comes to solving a problem, developers often tend to use the technologies they’re comfortable with — the technologies they work with on a daily basis. Most of the time this is fine — we work within a specific scope in which this technology makes sense and has already…

A distributed computation system for deep learning experiments with Docker Compose and RabbitMQ.

Lifting our 2,000 favorite tracks limit

Co-authored by Virgile Carron Adding tracks to favorites is one of Deezer’s most important features. It’s been here for ten years now. It’s the best way to save the content that you love and above all to help us suggest awesome music according to your tastes. It’s also the essence…

Lyrics in French Hip-hop: curious? IAM, and you should be too.

Introduction In 2018, hip-hop was the most consumed genre in the United States. Since then, many analyses have dived deep in understanding the lyrics of those artists. However, as the pioneer of music streaming in France, we wanted to know more about how our local stars created their art. With the…

Updating Kubernetes CA certificates the hard way

So buckle up; it might be a bumpy ride! The hard way yes, but automated! At Deezer, Kubernetes has…

‘Hey Siri, play my Flow on Deezer’ (part 1.): a product introduction

Voice interactive devices and services have significantly spread over the last four years. Consequently, voice assistants have become smarter and more sophisticated in their ability to handle new and complex demands. Moreover, voice assistance has also become an available feature in more and more devices. In 2018, Apple announced that…

Engines revving for my first hackathon!

Since the previous…

HAMR@ISMIR2018 — Deezer HQ

We hosted the 2018 ISMIR edition of the HAMR Hackathon. It was awesome, people from all over the world collaborated on fun and innovative research topics during two days. A lot of very cool projects emerged. Most of them won’t stick but some will, and that -you have to admit…

Deezer at ICASSP 2017

I went to ICASSP in New Orleans to present a (small) part of the research done at Deezer in the R&D team. It was the opportunity to exchange with the community and gather much valuable knowledge and ideas. Our work was about using Convolutional Neural Networks (CNNs) to solve a…

From a few insights to a key feature

Product conception is based on a multitude of factors: data analytics, market research, benchmark, feedback from users/stores/customer support, user testing, intuition…And it always requires a few steps (and sometimes more than expected) to go from the initial concept or hypothesis to the final product pushed to all users. During my…

Women’s Voices — A Data Story

Part. 1: Women’s Voices — A Product Story Part. 2: Women’s Voices — A Brand Story Part. 3: Women’s Voices — A Data Story Part. 4: Women’s Voices — A…