Inspired by the respective human capacity, this paper investigates learning through analogies via the reservoir computing paradigm. Even though the vast majority of the literature considers modeling of patterns/objects serving classification-based applications, we move to learning of relationships characterizing input pairs. To this end, we describe the design process of a suitable echo state network capturing relationships existing between audio signals, i.e. similar, dissimilar, reverberation, and noise. Such a neural network operates on frequency-domain representations of sound belonging to the following four classes: male and female speech, applause and laughter. After extensive experiments, we demonstrate that echo state networks are able to learn through analogies and achieve superior performance when compared with Siamese neural networks.

Learning relationships between audio signals based on reservoir networks / S. Ntalampiras (PROCEEDINGS OF ... INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS). - In: 2022 International Joint Conference on Neural Networks (IJCNN)[s.l] : IEEE, 2022. - ISBN 978-1-7281-8671-9. - pp. 1-6 (( convegno IJCNN tenutosi a Padova nel 2022 [10.1109/IJCNN55064.2022.9892009].

Learning relationships between audio signals based on reservoir networks

S. Ntalampiras
2022

Abstract

Inspired by the respective human capacity, this paper investigates learning through analogies via the reservoir computing paradigm. Even though the vast majority of the literature considers modeling of patterns/objects serving classification-based applications, we move to learning of relationships characterizing input pairs. To this end, we describe the design process of a suitable echo state network capturing relationships existing between audio signals, i.e. similar, dissimilar, reverberation, and noise. Such a neural network operates on frequency-domain representations of sound belonging to the following four classes: male and female speech, applause and laughter. After extensive experiments, we demonstrate that echo state networks are able to learn through analogies and achieve superior performance when compared with Siamese neural networks.
Settore INF/01 - Informatica
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
Learning_relationships_between_audio_signals_based_on_reservoir_networks.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 912.25 kB
Formato Adobe PDF
912.25 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/939369
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact