论文信息 - An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting

An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting

Nearly all previous work on small-footprint keyword spotting with neural networks quantify model footprint in terms of the number of parameters and multiply operations for a feedforward inference pass. These values are, however, proxy measures since empirical performance in actual deployments is determined by many factors. In this paper, we study the power consumption of a family of convolutional neural networks for keyword spotting on a Raspberry Pi. We find that both proxies are good predictors of energy usage, although the number of multiplies is more predictive than the number of model parameters. We also confirm that models with the highest accuracies are, unsurprisingly, the most power hungry.

[1] Tara N. Sainath,et al. Convolutional neural networks for small-footprint keyword spotting , 2015, INTERSPEECH.

[2] Sercan Ömer Arik,et al. Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting , 2017, INTERSPEECH.

[3] Georg Heigold,et al. Small-footprint keyword spotting using deep neural networks , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4] Nikko Strom,et al. Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

[5] Eugenio Culurciello,et al. An Analysis of Deep Neural Network Models for Practical Applications , 2016, ArXiv.

[6] Jimmy J. Lin,et al. Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting , 2017, ArXiv.