In this work we propose a deep learning based method—namely, variational, convolutional recurrent autoencoders (VCRAE)—for musical instrument synthesis. This method utilizes the higher level time-frequency representations extracted by the convolutional and recurrent layers to learn a Gaussian distribution in the training stage, which will be later used to infer unique samples through interpolation of multiple instruments in the usage stage. The reconstruction performance of VCRAE is evaluated by proxy through an instrument classifier and provides significantly better accuracy than two other baseline autoencoder methods. The synthesized samples for the combinations of 15 different instruments are available on the companion website.
Authors:
Çakir, Emre; Virtanen, Tuomas
Affiliation:
Tampere University of Technology, Tampere, Finland
AES Convention:
145 (October 2018)
Paper Number:
10035
Publication Date:
October 7, 2018
Subject:
Signal Processing—Part 1
Click to purchase paper as a non-member or you can login as an AES member to see more options.
No AES members have commented on this paper yet.
To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.