{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:20:08Z","timestamp":1791393608116,"version":"4.3.3"},"reference-count":44,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Scientific Research Startup Fund for High-Level Introduced Talents","award":["NY219143"],"award-info":[{"award-number":["NY219143"]}]},{"name":"Scientific Research Startup Fund for High-Level Introduced Talents","award":["XK1060919143"],"award-info":[{"award-number":["XK1060919143"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Keyword spotting (KWS) systems based on Spike Neural Networks (SNNs) offer a promising solution for always-on voice interfaces. However, achieving a favorable trade-off between computational footprint and recognition accuracy remains challenging for resource-constrained edge devices. This paper proposes a lightweight convolutional spiking neural network (CSNN) for KWS that combines a streamable Mel-to-Spike encoder, a convolutional spiking feature extractor, and a delay-aware classification module that uses learnable synaptic delays. The proposed encoder adopts streaming frame-by-frame encoding to convert speech features into sparse spike trains, while the delay-aware classifier jointly optimizes synaptic weights and temporal delays for enhanced spatiotemporal evidence aggregation. Experiments on the Google Speech Commands V1 and V2 (GSC-V1 and GSC-V2), Heidelberg Digits (HD), and Chinese Mandarin Keyword (CMK) datasets show mean test accuracies of 94.37%, 92.87%, 99.10%, and 95.60%, respectively. The proposed method uses only 64.05 K and 68.14 K learnable parameters for the 12-class and 20-class classification, while maintaining strong robustness to additive noise. These results indicate that the proposed CSNN achieves a favorable algorithm-level balance among accuracy, compactness, and noise robustness for KWS.<\/jats:p>","DOI":"10.3390\/s26144514","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:12:38Z","timestamp":1784257958000},"page":"4514","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Lightweight Keyword Spotting Method Using a Convolutional Spiking Neural Network with Learnable Synaptic Delays"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5623-7670","authenticated-orcid":false,"given":"Xiaohuan","family":"Li","sequence":"first","affiliation":[{"name":"College of Integrated Circuit Science and Engineering, Nanjing University of Posts and Telecommunication, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Integrated Circuit Science and Engineering, Nanjing University of Posts and Telecommunication, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Libo","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Integrated Circuit Science and Engineering, Nanjing University of Posts and Telecommunication, Nanjing 210023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4169","DOI":"10.1109\/ACCESS.2021.3139508","article-title":"Deep Spoken Keyword Spotting: An Overview","volume":"10","author":"Tan","year":"2022","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bae, S., Kim, H., Lee, S., and Jung, Y. (2023). FPGA Implementation of Keyword Spotting System Using Depthwise Separable Binarized and Ternarized Neural Networks. Sensors, 23.","DOI":"10.3390\/s23125701"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Chen, G., Parada, C., and Heigold, G. (2014). Small-footprint keyword spotting using deep neural networks. Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, 4\u20139 May 2014, IEEE.","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Sigtia, S., Haynes, R., Richards, H., Marchi, E., and Bridle, J. (2018). Efficient Voice Trigger Detection for Low Resource Hardware. Proceedings of the Interspeech 2018, Hyderabad, India, 2\u20136 September 2018, ISCA.","DOI":"10.21437\/Interspeech.2018-2204"},{"key":"ref_5","unstructured":"Lengerich, C., and Hannun, A. (2016). An End-to-End Architecture for Keyword Spotting and Voice Activity Detection. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shen, Y., Wu, B., Straeussnigg, D., and Gutierrez, E. (2025). A KWS System for Edge-Computing Applications with Analog-Based Feature Extraction and Learned Step Size Quantized Classifier. Sensors, 25.","DOI":"10.20944\/preprints202503.0510.v1"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/978-3-030-86383-8_20","article-title":"End-to-End Spiking Neural Network for Speech Recognition Using Resonating Input Neurons","volume":"Volume 12895","author":"Auge","year":"2021","journal-title":"Artificial Neural Networks and Machine Learning\u2014ICANN 2021"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","article-title":"Networks of Spiking Neurons: The Third Generation of Neural Network Models","volume":"10","author":"Maass","year":"1997","journal-title":"Neural Netw."},{"key":"ref_9","first-page":"5112","article-title":"Temporal-Channel Joint Attention for Spiking Neural Networks","volume":"35","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1109\/TNNLS.2021.3110991","article-title":"Rectified Linear Postsynaptic Potential Function for Backpropagation in Deep Spiking Neural Networks","volume":"33","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"M\u00e9sz\u00e1ros, B., Knight, J.C., and Nowotny, T. (2024). Learning Delays through Gradients and Structure: Emergence of Spatiotemporal Patterns in Spiking Neural Networks. Front. Comput. Neurosci., 18.","DOI":"10.3389\/fncom.2024.1460309"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhang, D., Shi, K., Wang, Y., Wei, W., Wu, J., and Zhang, M. (2024). Global-Local Convolution with Spiking Neural Networks for Energy-Efficient Keyword Spotting. Proceedings of the Interspeech 2024, Kos, Greece, 1\u20135 September 2024, ISCA.","DOI":"10.21437\/Interspeech.2024-642"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Garai, S., and Samui, S. (2025). Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms. arXiv.","DOI":"10.1016\/j.neucom.2026.134028"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2744","DOI":"10.1109\/TNNLS.2020.3044364","article-title":"The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks","volume":"33","author":"Cramer","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5776","DOI":"10.1038\/s41467-025-60878-z","article-title":"Advancing spatio-temporal processing through adaptation in spiking neural networks","volume":"16","author":"Baronig","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107154","DOI":"10.1016\/j.neunet.2025.107154","article-title":"Towards Parameter-Free Attentional Spiking Neural Networks","volume":"185","author":"Sun","year":"2025","journal-title":"Neural Netw."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Stewart, K.M., Shea, T.M., Pacik-Nelson, N., Gallo, E., and Danielescu, A. (2023). Speech2Spikes: Efficient Audio Encoding Pipeline for Real-Time Neuromorphic Systems. Proceedings of the Neuro-Inspired Computational Elements Conference (NICE 2023), San Antonio, TX, USA, 11\u201314 April 2023, ACM Digital Library.","DOI":"10.1145\/3584954.3584995"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yang, Q., Liu, Q., and Li, H. (2022). Deep Residual Spiking Neural Network for Keyword Spotting in Low-Resource Settings. Proceedings of the Interspeech 2022, Incheon, Republic of Korea, 18\u201322 September 2022, ISCA.","DOI":"10.21437\/Interspeech.2022-107"},{"key":"ref_19","unstructured":"Hammouamri, I., Khalfaoui-Hassani, I., and Masquelier, T. (2024, January 7\u201311). Learning Delays in Spiking Neural Networks Using Dilated Convolutions with Learnable Spacings. Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria. Available online: https:\/\/openreview.net\/forum?id=4r2ybzJnmN."},{"key":"ref_20","first-page":"124","article-title":"Accurate, Guaranteed Stable, Sliding Discrete Fourier Transform","volume":"27","author":"Duda","year":"2010","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Song, Z., Liu, Q., Yang, Q., Peng, Y., and Li, H. (2024). ED-sKWS: Early-Decision Spiking Neural Networks for Rapid, and Energy-Efficient Keyword Spotting. Proceedings of the Interspeech 2024, Kos, Greece, 1\u20135 September 2024, ISCA.","DOI":"10.21437\/Interspeech.2024-1609"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Pellegrini, T., Zimmer, R., and Masquelier, T. (2021). Low-Activity Supervised Convolutional Spiking Neural Networks Applied to Speech Commands Recognition. Proceedings of the 2021 IEEE Spoken Language Technology Workshop (SLT), Shenzhen, China, 19\u201322 January 2021, IEEE.","DOI":"10.1109\/SLT48900.2021.9383587"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yao, M., Gao, H., Zhao, G., Wang, D., Lin, Y., Yang, Z., and Li, G. (2021). Temporal-Wise Attention Spiking Neural Networks for Event Streams Classification. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, 10\u201317 October 2021, IEEE.","DOI":"10.1109\/ICCV48922.2021.01006"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wu, Y., Deng, L., Li, G., Zhu, J., Xie, Y., and Shi, L. (2019). Direct Training for Spiking Neural Networks: Faster, Larger, Better. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), Honolulu, HI, USA, 27 January\u20131 February 2019, AAAI Press.","DOI":"10.1609\/aaai.v33i01.33011311"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1007\/s13534-024-00404-0","article-title":"Spiking Neural Networks for Physiological and Speech Signals: A Review","volume":"14","author":"Park","year":"2024","journal-title":"Biomed. Eng. Lett."},{"key":"ref_26","unstructured":"Weidel, P., and Sheik, S. (2021). WaveSense: Efficient Temporal Convolutions with Spiking Neural Networks for Keyword Spotting. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Gerstner, W., Kistler, W.M., Naud, R., and Paninski, L. (2014). Neuronal Dynamics: From Single Neurons to Networks and Models of Cognition, Cambridge University Press.","DOI":"10.1017\/CBO9781107447615"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Sun, P., Chua, Y., Devos, P., and Botteldooren, D. (2023). Learnable Axonal Delay in Spiking Neural Networks Improves Spoken Word Recognition. Front. Neurosci., 17.","DOI":"10.3389\/fnins.2023.1275944"},{"key":"ref_29","unstructured":"Warden, P. (2026, May 08). Speech Commands Dataset, Version 0.01. Available online: http:\/\/download.tensorflow.org\/data\/speech_commands_v0.01.tar.gz."},{"key":"ref_30","unstructured":"Warden, P. (2018). Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition. arXiv."},{"key":"ref_31","unstructured":"Warden, P. (2026, May 08). Speech Commands Dataset, Version 0.02. Available online: http:\/\/download.tensorflow.org\/data\/speech_commands_v0.02.tar.gz."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1109\/JPROC.2023.3308088","article-title":"Training Spiking Neural Networks Using Lessons from Deep Learning","volume":"111","author":"Eshraghian","year":"2023","journal-title":"Proc. IEEE"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Bittar, A., and Garner, P.N. (2022). A Surrogate Gradient Spiking Baseline for Speech Command Recognition. Front. Neurosci., 16.","DOI":"10.3389\/fnins.2022.865897"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1162\/neco_a_01367","article-title":"The Remarkable Robustness of Surrogate Gradient Learning for Instilling Complex Function in Spiking Neural Networks","volume":"33","author":"Zenke","year":"2021","journal-title":"Neural Comput."},{"key":"ref_35","unstructured":"Li, Q. (2024). Lightweight Computational Model for Keyword Spotting. Proceedings of the 2024 21st International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), IEEE."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shi, K., Lu, C., Liu, Y., Zhang, M., and Qu, H. (2023). Spatial-Temporal Self-Attention for Asynchronous Spiking Neural Networks. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23), Macao, China, 19\u201325 August 2023, IJCAI.","DOI":"10.24963\/ijcai.2023\/344"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Orchard, G., Frady, E.P., Rubin, D.B.D., Sanborn, S., Shrestha, S.B., Sommer, F.T., and Davies, M. (2021). Efficient Neuromorphic Signal Processing with Loihi 2. 2021 IEEE Workshop on Signal Processing Systems (SiPS), IEEE.","DOI":"10.1109\/SiPS52927.2021.00053"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Dampfhoffer, M., Mesquida, T., Hardy, E., Valentian, A., and Anghel, L. (2023). Leveraging Sparsity with Spiking Recurrent Neural Networks for Energy-Efficient Keyword Spotting. Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE.","DOI":"10.1109\/ICASSP49357.2023.10097174"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., and Aydin, M. (2022). Investigating Current-Based and Gating Approaches for Accurate and Energy-Efficient Spiking Recurrent Neural Networks. Artificial Neural Networks and Machine Learning\u2013ICANN 2022, Springer Nature.","DOI":"10.1007\/978-3-031-15934-3"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Patino-Saucedo, A., Yousefzadeh, A., Tang, G., Corradi, F., Linares-Barranco, B., and Sifalakis, M. (2023). Empirical Study on the Efficiency of Spiking Neural Networks with Axonal Delays, and Algorithm-Hardware Benchmarking. 2023 IEEE International Symposium on Circuits and Systems (ISCAS), IEEE.","DOI":"10.1109\/ISCAS46773.2023.10181778"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1038\/s42256-021-00397-w","article-title":"Accurate and Efficient Time-Domain Classification with Adaptive Spiking Recurrent Neural Networks","volume":"3","author":"Yin","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"ref_42","unstructured":"Sabbella, H., Mukherjee, A., Kandappu, T., Dey, S., Pal, A., Misra, A., and Ma, D. (2025). The Promise of Spiking Neural Networks for Ubiquitous Computing: A Survey and New Perspectives. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Alvarez, R., and Park, H.-J. (2019). End-to-End Streaming Keyword Spotting. Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 12\u201317 May 2019, IEEE.","DOI":"10.1109\/ICASSP.2019.8683557"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Y\u0131lmaz, E., Gevrek, \u00d6.B., Wu, J., Chen, Y., Meng, X., and Li, H. (2020). Deep Convolutional Spiking Neural Networks for Keyword Spotting. Proceedings of the Interspeech 2020, Shanghai, China, 25\u201329 October 2020, ISCA.","DOI":"10.21437\/Interspeech.2020-1230"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4514\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:26:51Z","timestamp":1784258811000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,16]]},"references-count":44,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144514"],"URL":"https:\/\/doi.org\/10.3390\/s26144514","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,16]]}}}