Real-time black-box modelling with recurrent neural networks

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu

Tutkijat

Organisaatiot

Kuvaus

This paper proposes to use a recurrent neural network for black-box modelling of nonlinear audio systems, such as tube amplifiers and distortion pedals. As a recurrent unit structure, we test both Long Short-Term Memory and a Gated Recurrent Unit. We compare the proposed neural network with a WaveNet-style deep neural network, which has been suggested previously for tube amplifier modelling. The neural networks are trained with several minutes of guitar and bass recordings, which have been passed through the devices to be modelled. A real-time audio plugin implementing the proposed networks has been developed in the JUCE framework. It is shown that the recurrent neural networks achieve similar accuracy to the WaveNet model, while requiring significantly less processing power to run. The Long Short-Term Memory recurrent unit is also found to outperform the Gated Recurrent Unit overall. The proposed neural network is an important step forward in computationally efficient yet accurate emulation of tube amplifiers and distortion pedals.

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoProceedings of the International Conference on Digital Audio Effects
TilaJulkaistu - 2 syyskuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Conference on Digital Audio Effects - Birmingham, Iso-Britannia
Kesto: 2 syyskuuta 20196 syyskuuta 2019
Konferenssinumero: 22

Julkaisusarja

NimiProceedings of the International Conference on Digital Audio Effects
ISSN (painettu)2414-6382
ISSN (elektroninen)2413-6689

Conference

ConferenceInternational Conference on Digital Audio Effects
LyhennettäDAFX
MaaIso-Britannia
KaupunkiBirmingham
Ajanjakso02/09/201906/09/2019

Lataa tilasto

Ei tietoja saatavilla

ID: 36768416