Modern smartphones are equipped with powerful audio hardware and processors, allowing them to acquire and perform on-device speech processing at high sampling rates. However, energy consumption remains a concern, especially for resource-intensive DNNs. Prior mobile speech processing reduced computational complexity by compacting the model or reducing input dimensions via hyperparameter tuning, which reduced accuracy or required more training iterations. This paper proposes gradient descent for optimizing energy-efficient speech recording format (length and sampling rate). The goal is to reduce the input size, which reduces data collection and inference energy. For a backward pass, a masking function with non-zero derivatives (Gaussian, Hann, and Hamming) is used as a windowing function and a lowpass filter. An energy-efficient penalty is introduced to incentivize the reduction of the input size. The proposed masking outperformed baselines by 8.7% in speaker recognition and traumatic brain injury detection using 49% shorter duration, sampled at a lower frequency.

翻译：现代智能手机配备了强大的音频硬件和处理器，使其能够以高采样率获取并执行设备端语音处理。然而，能耗问题依然令人关注，尤其是对于资源密集型的深度神经网络。先前的移动端语音处理方法通过压缩模型或调整超参数降低输入维度来减少计算复杂度，但这会导致精度下降或需要更多训练迭代。本文提出使用梯度下降方法优化节能语音记录格式（时长与采样率），目标是通过减小输入尺寸来降低数据采集与推理能耗。在反向传播过程中，采用具有非零导数的掩蔽函数（高斯窗、汉宁窗和海明窗）作为窗函数与低通滤波器，并引入节能惩罚项以激励输入尺寸的缩减。实验表明，所提掩蔽方法在说话人识别与创伤性脑损伤检测任务中，使用49%的更短时长与更低频率采样，相较基线方法实现了8.7%的性能提升。