【摘要】 随着深度学习技术的发展，自动语音识别任务模型的参数数量越来越庞大，使得模型的计算开销、存储需求和功耗花费逐渐增加，难以在资源受限设备上部署.因此对基于深度学习的自动语音识别模型进行压缩，在降低模型大小的同时尽量保持原有性能具有重要价值.针对上述问题，全面综述了近年来该领域的主要工作，将其归纳为知识蒸馏、模型量化、低秩分解、网络剪枝、参数共享以及组合模型几类方法，并进行了系统综述，为模型在资源受限设备的部署提供可选的解决方案.更多还原

【Abstract】 With the development of deep learning technology, the number of parameters in automatic speech recognition task models was becoming increasingly large, which gradually increased the computing overhead, storage requirements and power consumption of the models, and it was difficult to deploy on resource-constrained devices. Therefore, it was of great value to compress the automatic speech recognition models based on deep learning to reduce the size of the modes while maintaining the original performance as much as possible. Aiming at the above problems, a comprehensive survey was conducted on the main works in this field in recent years, which was summarized as several methods, including knowledge distillation, model quantization, low-rank decomposition, network pruning, parameter sharing and combination models, and conducted a systematic review to provide alternative solutions for the deployment of models on resource-constrained devices.更多还原