Parallel Conformer Speech Enhancement Supports Low Power Hearing Aid Chips with Efficient Low Latency Attention
DOI:
https://doi.org/10.66421/int.j.datasci.intell.syst41Keywords:
Speech Enhancement, Hearing Aids, Parallel Conformer, Edge ComputingAbstract
Sensorineural hearing loss represents a profound global health challenge, significantly diminishing the quality of life for millions of individuals by impeding their ability to understand speech in acoustically complex environments. Modern hearing aids mitigate these deficits through amplification, but traditional signal processing algorithms often struggle to separate target speech from non-stationary background noise. While deep learning has revolutionized speech enhancement, the deployment of highly capable models on hearing aid devices is severely restricted by stringent constraints on power consumption, computational capacity, memory footprint, and algorithmic latency. To address these interconnected challenges, this paper presents a novel Parallel Conformer architecture optimized explicitly for low-power hearing aid chips. By restructuring the standard sequential Conformer blocks into independent parallel branches for self-attention and convolution, the proposed model reduces computational latency while maintaining superior capacity to model both global contextual dependencies and local acoustic features. The architecture is further refined through hardware-aware optimization techniques, including post-training quantization and structured channel pruning, which drastically decrease memory requirements and active power draw. Extensive experimental evaluations demonstrate that the Parallel Conformer achieves high subjective and objective speech intelligibility scores, outperforming existing edge-based models while operating within a stringent one milliwatt power budget and a sub-five millisecond algorithmic latency window. These findings validate the feasibility of deploying advanced transformer-based architectures on severely resource-constrained auditory prosthetic devices.
References
1. Yu, H., Zhang, J., Chen, C., Xiang, T., Fang, Y., Niebles, J. C., & Adeli, E. (2026, March). Socialgen: Modeling multi-human social interaction with language models. In 2026 International Conference on 3D Vision (3DV) (pp. 1-17). IEEE.
2. Li, A., Liu, W., Luo, X., Yu, G., Zheng, C., & Li, X. (2021). A simultaneous denoising and dereverberation framework with target decoupling. arXiv preprint arXiv:2106.12743.
3. Zhang, J., Chen, C., Chen, X., Yu, H., Xiang, T., Khan, A. S., ... & Adeli, E. (2026). Vibes: A conversational agent with behaviorally-intelligent 3d virtual body. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 39994-40008).
4. Zhang, H., Chen, J., Wu, D., Li, Y., Zhang, Y., Zhang, X. T., ... & Tian, F. (2026). Duplexsla: A full-duplex spoken language model with synchronized speech, language, and action. arXiv preprint arXiv:2605.20755.
5. Xu, X. (2024). Improving monaural speech enhancement by mapping to fixed simulation space with knowledge distillation. IEEE Signal Processing Letters, 31, 386-390.
6. Wu, D., Zhang, H., Chen, J., Liu, H., Chng, E. S., Tian, F., ... & Yu, G. (2025). Mind-Paced Speaking: A Dual-Brain Approach to Real-Time Reasoning in Spoken Language Models. arXiv preprint arXiv:2510.09592.
7. van den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., et al. (2016). WaveNet: A generative model for raw audio. arXiv preprint arXiv:1609.03499.
8. Dai, L., Li, A., Chi, C., Liang, Y., Li, X., & Zheng, C. (2026). GOMPSNR: Reflourish the Signal-to-Noise Ratio Metric for Audio Generation Tasks. arXiv preprint arXiv:2601.13758.
9. Xu, X., Tu, W., & Yang, Y. (2023). CASE-Net: Integrating local and non-local attention operations for speech enhancement. Speech Communication, 148, 31-39.
10. Chen, C., Zhang, J., Lakshmikanth, S. K., Fang, Y., Shao, R., Wetzstein, G., ... & Adeli, E. (2025). The language of motion: Unifying verbal and non-verbal language of 3d human motion. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 6200-6211).
11. Li, A., Lei, T., Sun, Z., Chen, R., Yin, E., Li, X., & Zheng, C. (2025). Learning neural vocoder from range-null space decomposition. arXiv preprint arXiv:2507.20731.
12. Xu, Xinmeng, et al. "Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning." arXiv preprint arXiv:2605.01673 (2026).
13. Dai, S., Wu, Y., Chen, S., Huang, R., & Dannenberg, R. B. (2023, November). SingStyle111: A Multilingual Singing Dataset With Style Transfer. In ISMIR (pp. 765-773).
14. Xu, X., Tu, W., & Yang, Y. (2024). Adaptive selection of local and non-local attention mechanisms for speech enhancement. Neural Networks, 174, 106236.
15. Li, A., Zheng, C., Zhang, L., & Li, X. (2022). Glance and gaze: A collaborative learning framework for single-channel speech enhancement. Applied Acoustics, 187, 108499.
16. Lv, Z., Wang, Q., Lyu, T., & Dong, J. (2026). A Deep Learning-Based Model for User Emotion Recognition and Behavior Guidance Design: EMoGuideNet-An Emotion-Aware Multimodal Framework for Enhancing Intelligent User Interaction. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-30.
17. Chen, L. (2026). Beyond external constraints: The missing dimension of ai governance. Available at SSRN 6449738.
18. Xu, Xinmeng, Weiping Tu, and Yuhong Yang. "Pcnn: A lightweight parallel conformer neural network for efficient monaural speech enhancement." arXiv preprint arXiv:2307.15251 (2023).
19. Xu, X., Tu, W., & Yang, Y. (2025). Efficient audio–visual information fusion using encoding pace synchronization for Audio–Visual Speech Separation. Information Fusion, 115, 102749.
20. Xu, X., Li, J., Zhang, Y., Tu, W., & Yang, Y. (2025). Spatial information aided speech and noise feature discrimination for Monaural speech enhancement. Expert Systems with Applications, 269, 126349.
21. Li, A., Liu, W., Zheng, C., Fan, C., & Li, X. (2021). Two heads are better than one: A two-stage complex spectral mapping approach for monaural speech enhancement. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1829-1843.
22. Li, A., Yu, G., Zheng, C., Liu, W., & Li, X. (2023). A general unfolding speech enhancement method motivated by Taylor's theorem. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, 3629-3646.
23. Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2023). Robust speech recognition via large-scale weak supervision. In Proceedings of ICML.
24. Xu, X., Zhang, Y., Li, J., Yang, Y., Luo, Y., & Tu, W. (2025). FIRING-Net: A filtered feature recycling network for speech enhancement. In The Thirteenth International Conference on Learning Representations.
25. Zhang, H., Liu, H., Zhang, X., Zhang, Q., Hu, Y., Zhao, J., ... & Chng, E. S. (2025). Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English. arXiv preprint arXiv:2505.17076.
26. Li, A., Sun, Z., Hao, F., Li, X., & Zheng, C. (2025). Neural vocoders as speech enhancers. arXiv preprint arXiv:2501.13465.
27. Xu, X., Tu, W., & Yang, Y. (2023, June). Selector-enhancer: learning dynamic selection of local and non-local attention operation for speech enhancement. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 11, pp. 13853-13860).
28. Li, A., Liu, W., Zheng, C., & Li, X. (2022, May). Embedding and beamforming: All-neural causal beamformer for multichannel speech enhancement. In ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 6487-6491). IEEE.
29. Xu, X., Han, C., Zhang, Y., Tu, W., & Yang, Y. (2024, April). Curricular Contrastive Regularization for Speech Enhancement with Self-Supervised Representations. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 10486-10490). IEEE.
30. Xu, X., Wang, Y., Xu, D., Peng, Y., Zhang, C., Jia, J., & Chen, B. (2022, May). Vsegan: Visual speech enhancement generative adversarial network. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7308-7311). IEEE.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Claire Aubert, Daichi Nomura, Sophie Morel, Mathieu Girard

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All articles are published under the Creative Commons Attribution 4.0 (CC BY 4.0) License. Users may share, copy, adapt, and distribute the work for any purpose, provided proper credit is given to the original author(s) and source. Authors retain copyright.
