Power consumption plays an important role in on-device streaming speech recognition, as it has a direct impact on the user experience. This study delves into how weight parameters in speech recognition models influence the overall power consumption of these models. We discovered that the impact of weight parameters on power consumption varies, influenced by factors including how often they are invoked and their placement in memory. Armed with this insight, we developed design guidelines aimed at optimizing on-device speech recognition models. These guidelines focus on minimizing power use without substantially affecting accuracy. Our method, which employs targeted compression based on the varying sensitivities of weight parameters, demonstrates superior performance compared to state-of-the-art compression methods. It achieves a reduction in energy usage of up to 47% while maintaining similar model accuracy and improving the real-time factor.

在本研究中，我们探讨了权重参数对语音识别模型整体功率消耗的影响，发现权重参数对功率消耗的影响因多种因素而异，包括调用频率和内存中的位置。基于这一洞察，我们制定了旨在优化设备内语音识别模型的设计准则，着重于在不实质影响准确性的情况下最小化功耗。我们的方法采用针对不同权重参数敏感性的有针对性压缩，相比于最先进的压缩方法，它在保持类似模型准确性的同时，实现了最高47%的能量使用减少，并改善了实时性。

不是所有的权重都是平等的：增强设备上流式语音识别的能效