Spatiotemporal audio feature extraction with dynamic memristor-based time-surface neurons

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Neuromorphic speech recognition systems that use spiking neural networks (SNNs) and memristors are progressing in hardware development. The conventional manual preprocessing of audio signals is shifting toward event-based recognition with convolutional SNNs. Despite achieving high accuracy in classification, the efficient extraction of spatiotemporal features from audio events continues to be a substantial challenge. In this study, we introduce dynamic time-surface neurons (DTSNs) using volatile memristors featuring an adjustable temporal kernel decay, enabled by series-connected transistors with an Au/LiCoO ₂/Au configuration. DTSNs act as feature descriptors, enhancing the spatiotemporal feature extraction from event audio data. A two-layer SNN classifier, fully connected and incorporating a 1T1R nonvolatile memristor array, is trained to recognize the spatiotemporal features of the audio data. Our findings show classification accuracies of up to 95.91%, substantial improvements in computational efficiency, and increased noise resilience, confirming the promise of our memristor-based speech recognition system for practical applications.

Abstract

Memristor speech system with time-surface neurons enables highly efficient, precise audio processing.

Related collections

Most cited references 42

Record: found
Abstract: found
Article: not found

Synaptic plasticity: multiple forms, functions, and mechanisms.

Ami Citri, Robert Malenka (2008)

Experiences, whether they be learning in a classroom, a stressful event, or ingestion of a psychoactive substance, impact the brain by modifying the activity and organization of specific neural circuitry. A major mechanism by which the neural activity generated by an experience modifies brain function is via modifications of synaptic transmission; that is, synaptic plasticity. Here, we review current understanding of the mechanisms of the major forms of synaptic plasticity at excitatory synapses in the mammalian brain. We also provide examples of the possible developmental and behavioral functions of synaptic plasticity and how maladaptive synaptic plasticity may contribute to neuropsychiatric disorders.

0 comments Cited 568 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: not found
Article: not found

Fully hardware-implemented memristor convolutional neural network

Peng Yao, Huaqiang Wu, Bin Gao … (2020)

0 comments Cited 347 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: not found
Article: not found

Towards spike-based machine intelligence with neuromorphic computing

Kaushik Roy, Akhilesh Jaiswal, Priyadarshini Panda (2019)

0 comments Cited 248 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Contributors

Xulei Wu:

ORCID: https://orcid.org/0000-0002-9999-322X

Role: ConceptualizationRole: Data curationRole: Formal analysisRole: Funding acquisitionRole: InvestigationRole: MethodologyRole: Project administrationRole: ResourcesRole: SoftwareRole: SupervisionRole: ValidationRole: VisualizationRole: Writing - original draftRole: Writing - review & editing

Bingjie Dang: Role: ConceptualizationRole: Formal analysisRole: InvestigationRole: MethodologyRole: ResourcesRole: ValidationRole: VisualizationRole: Writing - original draft

Teng Zhang:

ORCID: https://orcid.org/0000-0003-2011-5940

Role: Formal analysisRole: InvestigationRole: MethodologyRole: ResourcesRole: ValidationRole: Writing - review & editing

Xiulong Wu:

ORCID: https://orcid.org/0000-0002-5012-2570

Role: ConceptualizationRole: Funding acquisitionRole: MethodologyRole: Project administrationRole: ResourcesRole: Supervision

Yuchao Yang:

ORCID: https://orcid.org/0000-0003-4674-4059

Role: ConceptualizationRole: Funding acquisitionRole: Project administrationRole: ResourcesRole: SupervisionRole: Writing - original draftRole: Writing - review & editing

Journal

Journal ID (nlm-ta): Sci Adv

Journal ID (iso-abbrev): Sci Adv

Journal ID (publisher-id): sciadv

Journal ID (hwp): advances

Title: Science Advances

Publisher: American Association for the Advancement of Science

ISSN (Electronic): 2375-2548

Publication date Collection: 05 April 2024

Publication date (Electronic, pub): 03 April 2024

Volume: 10

Issue: 14

Electronic Location Identifier: eadl2767

Affiliations

[ ¹ ]School of Integrated Circuits, Anhui University, Hefei 230601, China.

[ ² ]Beijing Advanced Innovation Center for Integrated Circuits, School of Integrated Circuits, Peking University, Beijing 100871, China.

[ ³ ]School of Electronic and Computer Engineering, Peking University, Shenzhen 518055, China.

[ ⁴ ]Center for Brain Inspired Intelligence, Chinese Institute for Brain Research (CIBR), Beijing, Beijing 102206, China.

[ ⁵ ]Center for Brain Inspired Chips, Institute for Artificial Intelligence, Frontiers Science Center for Nano-optoelectronics, Peking University, Beijing 100871, China.

Author notes

[* ]Corresponding author. Email: yuchaoyang@ 123456pku.edu.cn (Y.Y.); xiulong@ 123456ahu.edu.cn (X.W.)

[†]

These authors contributed equally to this work.

Author information

Xulei Wu https://orcid.org/0000-0002-9999-322X

Teng Zhang https://orcid.org/0000-0003-2011-5940

Xiulong Wu https://orcid.org/0000-0002-5012-2570

Yuchao Yang https://orcid.org/0000-0003-4674-4059

Article

Publisher ID: adl2767

DOI: 10.1126/sciadv.adl2767

PMC ID: 10990261

SO-VID: a1e35fb6-2126-4886-bfb5-72a07994f167

Copyright © Copyright © 2024 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC).

License:

This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license, which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited.