2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
| Paper ID | AUD-4.2 | ||
| Paper Title | Self-Supervised VQ-VAE For One-Shot Music Style Transfer | ||
| Authors | Ondřej Cífka, Télécom Paris, Institut Polytechnique de Paris, France; Alexey Ozerov, InterDigital R&D, France; Umut Şimşekli, Inria/ENS, France; Gaël Richard, Télécom Paris, Institut Polytechnique de Paris, France | ||
| Session | AUD-4: Music Signal Analysis, Processing, and Synthesis 2: Analysis and Processing | ||
| Location | Gather.Town | ||
| Session Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
| Presentation Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
| Presentation | Poster | ||
| Topic | Audio and Acoustic Signal Processing: [AUD-MSP] Music Signal Analysis, Processing and Synthesis | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Neural style transfer, allowing to apply the artistic style of one image to another, has become one of the most widely showcased computer vision applications shortly after its introduction. In contrast, related tasks in the music audio domain remained, until recently, largely untackled. While several style conversion methods tailored to musical signals have been proposed, most lack the 'one-shot' capability of classical image style transfer algorithms. On the other hand, the results of existing one-shot audio style transfer methods on musical inputs are not as compelling. In this work, we are specifically interested in the problem of one-shot timbre transfer. We present a novel method for this task, based on an extension of the vector-quantized variational autoencoder (VQ-VAE), along with a simple self-supervised learning strategy designed to obtain disentangled representations of timbre and pitch. We evaluate the method using a set of objective metrics and show that it is able to outperform selected baselines. | ||