电子学报2025，Vol.53Issue(10)：3483-3496,14.DOI:10.12263/DZXB.20250524
面向边缘设备的轻量化神经语音压缩方法
A Lightweight Neural Speech Compression Method for Edge Devices
摘要
Abstract
Neural audio compression methods have shown remarkable performance in low-bitrate speech reconstruc-tion,but their high computational cost and deployment complexity limit their practical use on edge devices.To address this issue,this paper proposes a lightweight neural speech compression system tailored for resource-constrained scenarios such as mobile terminals.Based on the Funcodec framework,we redesign the encoder module using a streamlined convolutional neural network architecture and introduce a multi-objective knowledge distillation strategy that integrates perceptual align-ment,spectral constraints and adversarial training.Experimental results demonstrate that the proposed convolutional neural network encoder significantly reduces model complexity and inference latency while maintaining comparable compression quality,enabling millisecond-level real-time speech encoding on edge devices.Furthermore,to improve transmission effi-ciency,we present a Huffman coding-based entropy optimization method that adaptively encodes residual quantization out-puts,achieving an average storage reduction of approximately 5%without compromising reconstruction quality.Overall,the proposed system strikes a favorable balance between compression fidelity,computational efficiency and deployability,making it well-suited for real-world speech acquisition and processing applications on edge platforms.关键词
音频压缩/哈夫曼编码/蒸馏学习/边缘计算Key words
audio compression/Huffman coding/knowledge distillation/edge computing分类
信息技术与安全科学引用本文复制引用
鲁昱,付永健,丁典,潘昊,薛广涛,任炬..面向边缘设备的轻量化神经语音压缩方法[J].电子学报,2025,53(10):3483-3496,14.基金项目
国家自然科学基金(No.62432004) National Natural Science Foundation of China(No.62432004) （No.62432004）
