Neural Drum Machine : An Interactive System for Real-time Synthesis of Drum Sounds - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Neural Drum Machine : An Interactive System for Real-time Synthesis of Drum Sounds

Résumé

In this work, we introduce a system for real-time generation of drum sounds. This system is composed of two parts: a generative model for drum sounds together with a Max4Live plugin providing intuitive controls on the generative process. The generative model consists of a Conditional Wasserstein autoencoder (CWAE), which learns to generate Mel-scaled magnitude spectrograms of short percussion samples, coupled with a Multi-Head Convolutional Neural Network (MCNN) which estimates the corresponding audio signal from the magnitude spectrogram. The design of this model makes it lightweight, so that it allows one to perform real-time generation of novel drum sounds on an average CPU, removing the need for the users to possess dedicated hardware in order to use this system. We then present our Max4Live interface designed to interact with this generative model. With this setup, the system can be easily integrated into a studio-production environment and enhance the creative process. Finally, we discuss the advantages of our system and how the interaction of music producers with such tools could change the way drum tracks are composed.

Dates et versions

hal-02479211 , version 1 (14-02-2020)

Identifiants

Citer

Cyran Aouameur, Philippe Esling, Gaëtan Hadjeres. Neural Drum Machine : An Interactive System for Real-time Synthesis of Drum Sounds. International Conference on Computational Creativity, Jun 2019, Charlotte, United States. ⟨hal-02479211⟩
97 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More