{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adaptive-axonal-delays-in-feedforward-spiking","title":"Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word recognition","arxiv_id":"2302.08607","date":"2023-02-16","proceeding":null,"authors":["Pengfei Sun","Ehsan Eqlimi","Yansong Chua","Paul Devos","Dick Botteldooren"],"abstract":"Spiking neural networks (SNN) are a promising research avenue for building accurate and efficient automatic speech recognition systems. Recent advances in audio-to-spike encoding and training algorithms enable SNN to be applied in practical tasks. Biologically-inspired SNN communicates using sparse asynchronous events. Therefore, spike-timing is critical to SNN performance. In this aspect, most works focus on training synaptic weights and few have considered delays in event transmission, namely axonal delay. In this work, we consider a learnable axonal delay capped at a maximum value, which can be adapted according to the axonal delay distribution in each network layer. We show that our proposed method achieves the best classification results reported on the SHD dataset (92.45%) and NTIDIGITS dataset (95.09%). Our work illustrates the potential of training axonal delays for tasks with complex temporal structures.","url_abs":"https://arxiv.org/abs/2302.08607v1","url_pdf":"https://arxiv.org/pdf/2302.08607v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-shd","task":"Audio Classification","dataset":"SHD","model":"SNN featuring learnable axonal delays with adaptively  delay caps","rank_in_archive_order":3,"of":11,"metrics":{"Percentage correct":"92.45"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.08607","atlas_url":"https://app.syntology.ai/?focus=2302.08607","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}