Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107478
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Computing | - |
dc.creator | Song, Z | en_US |
dc.creator | Wu, J | en_US |
dc.creator | Zhang, M | en_US |
dc.creator | Shou, MZ | en_US |
dc.creator | Li, H | en_US |
dc.date.accessioned | 2024-06-27T01:33:35Z | - |
dc.date.available | 2024-06-27T01:33:35Z | - |
dc.identifier.isbn | 979-8-3503-4485-1 | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/107478 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en_US |
dc.rights | The following publication Z. Song, J. Wu, M. Zhang, M. Z. Shou and H. Li, "Spiking-Leaf: A Learnable Auditory Front-End for Spiking Neural Networks," ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. 226-230 is available at https://doi.org/10.1109/ICASSP48485.2024.10446789. | en_US |
dc.subject | Learnable audio front-end | en_US |
dc.subject | Speech recognition | en_US |
dc.subject | Spike encoding | en_US |
dc.subject | Spiking neural networks | en_US |
dc.title | Spiking-leaf : a learnable auditory front-end for spiking neural networks | en_US |
dc.type | Conference Paper | en_US |
dc.identifier.spage | 226 | en_US |
dc.identifier.epage | 230 | en_US |
dc.identifier.doi | 10.1109/ICASSP48485.2024.10446789 | en_US |
dcterms.abstract | Brain-inspired spiking neural networks (SNNs) have demonstrated great potential for temporal signal processing. However, their performance in speech processing remains limited due to the lack of an effective auditory front-end. To address this limitation, we introduce Spiking-LEAF, a learnable auditory front-end meticulously designed for SNN-based speech processing. Spiking-LEAF combines a learnable filter bank with a novel two-compartment spiking neuron model called IHC-LIF. The IHC-LIF neurons draw inspiration from the structure of inner hair cells (IHC) and they leverage segregated dendritic and somatic compartments to effectively capture multi-scale temporal dynamics of speech signals. Additionally, the IHC-LIF neurons incorporate the lateral feedback mechanism along with spike regularization loss to enhance spike encoding efficiency. On keyword spotting and speaker identification tasks, the proposed Spiking-LEAF outperforms both SOTA spiking auditory front-ends and conventional real-valued acoustic features in terms of classification accuracy, noise robustness, and encoding efficiency. | - |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | 2024 IEEE International Conference on Acoustics, Speech,and Signal Processing : Proceedings : 14-19 April 2024, COEX, Seoul, Korea, p. 226-230 | en_US |
dcterms.issued | 2024 | - |
dc.relation.conference | International Conference on Acoustics, Speech, and Signal Processing [ICASSP] | - |
dc.description.validate | 202406 bcch | - |
dc.description.oa | Author’s Original | en_US |
dc.identifier.FolderNumber | a2887 | - |
dc.identifier.SubFormID | 48649 | - |
dc.description.fundingSource | RGC | en_US |
dc.description.fundingSource | Others | en_US |
dc.description.fundingText | National Natural Science Foundation of China | en_US |
dc.description.pubStatus | Published | en_US |
dc.description.oaCategory | Green (AO) | en_US |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Song_Spiking-leaf_Learnable_Auditory.pdf | Preprint version | 1.19 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.