CxLSTM: Deploying xLSTM-Based Custom Keyword Spotting to Edge Devices
Keyword spotting (KWS) serves as the critical entry point for voice interaction in intelligent systems. Traditional KWS systems rely on predefined keywords with limited customization, whereas existing custom keyword spotting (CKWS) approaches incur heavy computational overhead, limiting their deployment on resource-limited edge devices. To address these challenges, we present CxLSTM, an optimized extended LSTM module with only 57.6K parameters, 318.6 KB static memory, 593.1 KB peak memory, and 3.54 MACs per inference. Based on CxLSTM, we propose an on-device CKWS method and perform extensive experiments. In offline evaluation, the proposed method obtains an equal error rate (EER) of 0.27 and an area under the ROC curve (AUC) of 0.78 on the public Google Speech Commands V2 dataset. Superior performance is further validated on a private Mandarin dataset, yielding an EER of 0.06 and an AUC of 0.98. Furthermore, in real-world tests for Mandarin CKWS across three scenarios, the proposed method achieves a recognition accuracy above 95% on Android devices, with a false alarm rate below 0.75/24 h and an average latency of 2.1 ms. When deployed on STM32 microcontrollers, it maintains an accuracy of over 92.3%, with moderately increased false alarms (15.8/24 h) and latency (264.7 ms). Despite performance degradation on low-power microcontrollers due to limited hardware resources, the proposed CKWS method still enables efficient voice interaction on edge devices.
Authors
- Dan Deng (ORCID: https://orcid.org/0000-0001-7760-5663)
- Luyao Teng (ORCID: https://orcid.org/0000-0002-3872-4085)
- Chao Chang (ORCID: https://orcid.org/0000-0003-1139-4781)
- Xi Liu (ORCID: https://orcid.org/0000-0002-1110-2382)
- Haitao Cao (ORCID: https://orcid.org/0000-0002-8626-8686)
- Tianyou Xiao
Institutions
- Guangzhou Panyu Polytechnic (CN)
Publication Details
- Journal
- Journal of Advanced Computational Intelligence and Intelligent Informatics
- Published
- 2026-11-20
- DOI
- https://doi.org/10.20965/jaciii.2026.p2084
- Primary Topic
- Speech Recognition and Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 0.00