Canonical cortical graph neural networks and its application for speech enhancement in audio-visual hearing aids

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversity of Wolverhampton-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorEdinburgh Napier University-
Autor(es): dc.contributordeepCI.org 20/1 Parkside Terrace-
Autor(es): dc.creatorPassos, Leandro A.-
Autor(es): dc.creatorPapa, João Paulo-
Autor(es): dc.creatorHussain, Amir-
Autor(es): dc.creatorAdeel, Ahsan-
Data de aceite: dc.date.accessioned2025-08-21T20:22:45Z-
Data de disponibilização: dc.date.available2025-08-21T20:22:45Z-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-03-28-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.neucom.2022.11.081-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/249585-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/249585-
Descrição: dc.descriptionDespite the recent success of machine learning algorithms, most models face drawbacks when considering more complex tasks requiring interaction between different sources, such as multimodal input data and logical time sequences. On the other hand, the biological brain is highly sharpened in this sense, empowered to automatically manage and integrate such streams of information. In this context, this work draws inspiration from recent discoveries in brain cortical circuits to propose a more biologically plausible self-supervised machine learning approach. This combines multimodal information using intra-layer modulations together with Canonical Correlation Analysis, and a memory mechanism to keep track of temporal data, the overall approach termed Canonical Cortical Graph Neural networks. This is shown to outperform recent state-of-the-art models in terms of clean audio reconstruction and energy efficiency for a benchmark audio-visual speech dataset. The enhanced performance is demonstrated through a reduced and smother neuron firing rate distribution. suggesting that the proposed model is amenable for speech enhancement in future audio-visual hearing aid devices.-
Descrição: dc.descriptionCMI Lab School of Engineering and Informatics University of Wolverhampton-
Descrição: dc.descriptionDepartment of Computing São Paulo State University-
Descrição: dc.descriptionSchool of Computing Edinburgh Napier University, Scotland-
Descrição: dc.descriptiondeepCI.org 20/1 Parkside Terrace-
Descrição: dc.descriptionDepartment of Computing São Paulo State University-
Formato: dc.format196-203-
Idioma: dc.languageen-
Relação: dc.relationNeurocomputing-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectCanonical correlation analysis-
Palavras-chave: dc.subjectCortical circuits-
Palavras-chave: dc.subjectGraph neural network-
Palavras-chave: dc.subjectMultimodal learning-
Palavras-chave: dc.subjectPositional encoding-
Palavras-chave: dc.subjectPrior frames neighborhood-
Título: dc.titleCanonical cortical graph neural networks and its application for speech enhancement in audio-visual hearing aids-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.