Canary Vocal Sensorimotor Model with RNN Decoder and Low-dimensional GAN Generator - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Canary Vocal Sensorimotor Model with RNN Decoder and Low-dimensional GAN Generator

Abstract

Songbirds, like humans, learn to imitate sounds produced by adult conspecifics. Similarly, a complete vocal learning model should be able to produce, perceive and imitate realistic sounds. We propose (1) to use a low-dimensional generator model obtained from training WaveGAN on a canary vocalizations, (2) to use a RNN-classifier to model sensory processing. In this scenario, can a simple Hebbian learning rule drive the learning of the inverse model linking the perceptual space and the motor space? First, we study how the motor latent space topology affects the learning process. We then investigate the influence of the learning rate and of the motor latent space dimension. We observe that a simple Hebbian rule is able to drive the learning of realistic sounds produced via a low-dimensional GAN.
Fichier principal
Vignette du fichier
Pagliarini2021_ICDL_HAL-v1_Canary Vocal Sensorimotor Model with RNN Decoder and Low-dimensional GAN Generator.pdf (2.12 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03482372 , version 1 (15-12-2021)

Identifiers

  • HAL Id : hal-03482372 , version 1

Cite

Silvia Pagliarini, Arthur Leblois, Xavier Hinaut. Canary Vocal Sensorimotor Model with RNN Decoder and Low-dimensional GAN Generator. ICDL 2021- IEEE International Conference on Development and Learning, Aug 2021, Beijing, China. ⟨hal-03482372⟩

Relations

62 View
103 Download

Share

Gmail Mastodon Facebook X LinkedIn More