Deezer ORG

Deezer source separation library including pretrained models.

Your best buddy for keeping versions catalogs up to date!

Source code from the NeurIPS 2019 workshop article "Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks" (G. Salha, R. Hennequin, M. Vazirgiannis) + k-core framework implementation from IJCAI 2019 article "A Degeneracy Framework for Scalable Graph Autoencoders" (G. Salha, R. Hennequin, V.A. Tran, M. Vazirgiannis)

Samples for the Deezer Javascript SDK

DEPRECATED : A JS facade generator for KotlinJS / KMP

Code repository of our research paper - D. Afchar, G. Meseguer Brocal, R. Hennequin

Self-supervised key estimation model that matches performance with supervised state-of-the-art model.

Source code and data from the RecSys 2020 article "Carousel Personalization in Music Streaming Apps with Contextual Bandits" by W. Bendada, G. Salha and T. Bontempelli

A language detection Web Service

Repository to reproduce results of "Word2vec applied to Recommendation: Hyperparameters Matter" by H. Caselles-Dupré, F. Lesaint and J. Royo-Letelier. The paper will be published on the 12th ACM Conference on Recommender Systems, Vancouver, Canada, 2nd-7th October 2018

Source code from the KDD 2021 article "A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps" by L. Briand, G. Salha-Galvan, W. Bendada, M. Morlon and V.A. Tran

HTML5 Linter based on Google Style Guide

Code of our ISMIR 2025 paper - D. Afchar, G. Meseguer Brocal, K. Akesbi, R. Hennequin

Source code from the CIKM 2019 article "Gravity-Inspired Graph Autoencoders for Directed Link Prediction" by G. Salha, S. Limnios, R. Hennequin, V.A. Tran and M. Vazirgiannis

Sample application using Deezer Android SDK

A dataset of Valence/Arousal detection with deezer Id and MSD Id as input

Repository for the ISMIR 2024 Paper "STONE: Self-supervised Tonality Estimator".

Source code from the SIGIR 2023 article "Attention Mixtures for Time-Aware Sequential Recommendation" by V.A. Tran, G. Salha-Galvan, B. Sguerra, and R. Hennequin

Repository for the IEEE/ACM TASLP 2023 Paper "Zero-Note Samba: Self-Supervised Beat Tracking".

Tools to run experiments around large scale cover detection.

Source code from the article "FastGAE: Scalable Graph Autoencoders with Stochastic Subgraph Decoding" by G. Salha, R. Hennequin, J.B. Remy, M. Moussallam and M. Vazirgiannis (2020)

Python code for reproducing music genre translation experiments presented in the paper Leveraging knowledge bases and parallel annotations for music genre translation ISMIR 2019.

Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders (RecSys 2021)

Code to reproduce the experiments presented in the article "Data-Efficient Playlist Captioning With Musical and Linguistic Knowledge" (EMNLP 2022)

Code for reproducting the paper Music Augmentation and Denoising For Peak-Based Audio Fingerprinting

Improving Collaborative Metric Learning for Recommendation by a 2-stage negative sampling strategy.

Source code from our RecSys 2020 paper: "Making neural network interpretable with attribution: application to implicit signals prediction" (D. Afchar, R. Hennequin)

Code for reproducting experiments of the PISA paper published at RecSys 2024

DALI datasets split used to train models presented in the paper Multilingual lyrics-to-audio alignment (ISMIR 2020).

Research team website

Python code to reproduce the experiments presented in the paper Multilingual Music Genre Embeddings for Effective Cross-Lingual Music Item Annotation (ISMIR 2020).

Code to reproduce the experiments presented in the article "Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion" (Findings of ACL 2025)

Repository for the paper Improving Quotation Attribution with Fictional Character Embeddings, Gaspard Michel, Elena V. Epure, Romain Hennequin, Christophe Cerisara, EMNLP 2024 (Findings)

Repository for the ISMIR 2024 Paper "From Real to Cloned Singer Identification".

Code and data to reproduce the experiments presented in the article "A Human Subject Study of Named Entity Recognition (NER) in Conversational Music Recommendation Queries" (EACL 2023)

Unofficial Node.js wrapper for the Deezer API

G(r)oROTI is a selfhosted Return On Time Invested web application written in Go

Web interface application to visualize multilingual music genre embeddings and generated cross-lingual music genre annotations for Wikipedia music entities (artists, bands, albums, tracks).

Transfer the Million Song Dataset (MSD) in an Elasticsearch index

Code to reproduce the experiments presented in the article Topic Modeling on Podcast Short-Text Metadata (ECIR 2022)

An InApp notifications system for Windows Phone Silverlight applications.

Code and data to reproduce the experiments presented in the article "Harnessing High-Level Song Descriptors towards Natural Language-Based Music Recommendation" (NLP4MusA2024)

Code snippets of Deezer SDK / API

Template remover

Repository for paper "Multi-class-token transformer for multitask self-supervised music information retrieval"

Samples applications using Deezer iOS SDK in Objective-C & Swift

Repository for the ICASSP 2024 paper "An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging".

No description.

Code of our accepted ICML 2021 paper "Towards Rigorous Interpretations: a Formalisation of Feature Attribution" (D. Afchar, R. Hennequin, V. Guigue)

A stand-alone, x86 and x64 compatible, Windows version, of the chromaprint audio library.

Python code to reproduce the experiments presented in the article Modeling the Music Genre Perception across Language-Bound Cultures, presented at the EMNLP 2020 conference.

No description.

Hierarchical Latent Relation Modeling for Collaborative Metric Learning

No description.

No description.

Starter kit for getting started in the Music Demixing Challenge.

A collection of advices, ready to use via AOP

Code and data used in the paper "Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3" (NAACL 2025), co-authored by Gaspard Michel, Elena Epure, Romain Hennequin and Christophe Cerisara.

"Beyond the past": Leveraging Audio and Human Memory for Sequential Music Recommendation

This repository contains the dataset presented in the paper: "Beyond Musical Descriptors: Extracting Preference-Bearing Intent in Music Queries"

Pauses Prediction in text reading.

Code repository of our RecSys 2023 paper "Of Spiky SVDs and Music Recommendation" - D. Afchar, R. Hennequin, V. Guigue (2023)

Source code of our ISMIR 2022 paper "Learning Unsupervised Hierarchies of Audio Concepts" by D. Afchar, R. Hennequin and V. Guigue (2022)

This repository contains the code and data to reproduce the experiments from the article Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition presented at LREC 2022.

An Android sample application, using both GraceNote and Deezer SDK to match your music with Deezer's catalog

A Gradle plugin which enables AspectJ for Android builds

Windows Application Driver

A localization tool for your applications

No description.

No description.

Datasets splits for reproducing paper Singing Language Identification Using a Deep Phonotactic Approach (ICASSP 2021).

Supporting data for the paper: R. Hennequin, J. Royo Letelier, M. Moussallam "Audio Based Disambiguation Of Music Genre Tags", ISMIR 2018

Sample for the Deezer Cordova Plugin

A Plugin for cordova to embed JS apps within Android

A smart tool to provide diff/merge resolution for Java files

Code used for the paper "Synthetic Lyrics Detection Across Languages and Genres" (NAACL 2025 Workshop TrustNLP), co-authored by Yanis Labrak, Markus Frohmann, Gabriel Meseguer-Brocal, and Elena V. Epure.

Dataset for paper "Perceived femininity in singing voice: analysis and prediction"

No description.

Utilities and evaluation code for LibriQuote, a speech dataset of expressive utterances from fictional characters

No description.

No description.

No description.

Repository for the RecSys 2023 Paper "On the Consistency of Average Embeddings for Item Recommendation"

This repository will contain resources related to the RecSys 2025 EARL Workshop paper titled "Text2Playlist: Generating Personalized Playlists from Text on Deezer" by Mathieu Delcluze et al.

Deezer Homebrew tap

No description.

This repository will contain resources related to the ECIR 2024 Industry Talk titled "Let’s Get It Started: Fostering the Discoverability of New Releases on Deezer" by Léa Briand et al.

Code and data to reproduce the experiments presented in "Automatic Annotation of Direct Speech in Written French Narratives" (ACL 2023)

Token Generator for Edgecast Token-Based Authentication from Verizon Digital Media Services

No description.

Little helper to run Rancher Lab's k3s in Docker

No description.

No description.

No description.

Companion code repository for the CHIIR2024 paper "Modeling Activity-Driven Music Listening with PACE"

Deezer Debian repository

Code to reproduce the experiments presented in "Distinguishing Fictional Voices: a Study of Authorship Verification Models for Quotation Attribution" (LaTeCH-CLfl workshop at EACL 2024)

A conda-smithy repository for spleeter.

A conda-smithy repository for spleeter-gpu.

No description.