TY - JOUR A1 - Brodbeck, Frederic A1 - Seidler, Paul A1 - Hromada, Daniel T1 - Power Consumption of Diverse Speech Command Classification Methods on the Raspberry Pi Zero N2 - Abstract. This study compares performance of different speech com- mand classification systems which can be executed on an Raspberry Pi Zero ARMv6 architecture. Three systems are evaluated: first one, TREELITE_MFCC, is based on Treelite system cross-compiles a MFCC- classifying Random Forest into a highly optimized shared library; second, TFLITE_MFCC, performs classification of MFCC inputs by means of convolutional neural network encoded as a lightweight TensorFlow Lite model while the third one - labeled as TFLITE_RAW - uses more com- plex network to directly classify the audio signal. We evaluate models not only in terms of their accuracy and precision, but also in terms of execution time, voltage, current and energy consumed. We observe that while TFLITE_RAW offers superior performance in terms of accuracy, TREELITE_RAW is also worth of consideration for low-latency real- life applications since it offers relatively good performance (avg. micro- precision=0.917) but its predictions, when executed on Raspberry Pi Zero, are significantly faster and cost less energy than TensorFlow Lite models. KW - speech command classification, power consumption, ARMv6, random forests, TensorFlow Lite, TreeLite, precision-over-energy KW - Raspberry Pi Zero W KW - Automatische Spracherkennung Y1 - 2021 UR - https://opus4.kobv.de/opus4-udk/frontdoor/index/index/docId/1573 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b170-15735 SP - 1 EP - 14 ER -