Das Suchergebnis hat sich seit Ihrer Suchanfrage verändert. Eventuell werden Dokumente in anderer Reihenfolge angezeigt.
  • Treffer 4 von 58
Zurück zur Trefferliste

Power Consumption of Diverse Speech Command Classification Methods on the Raspberry Pi Zero

  • 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 RaspberryAbstract. 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.zeige mehrzeige weniger

Volltext Dateien herunterladen

Metadaten exportieren

Metadaten
Verfasserangaben: Frederic Brodbeck, Paul Seidler, Prof. Dr. Daniel HromadaORCiD
URN:urn:nbn:de:kobv:b170-15735
DOI:https://doi.org/10.25624/kuenste-1573
Dokumentart:Wissenschaftlicher Artikel
Sprache:Englisch
Datum der Veröffentlichung (online):01.07.2021
Datum der Erstveröffentlichung:01.07.2021
Veröffentlichende Institution:Universität der Künste Berlin
Datum der Freischaltung:01.06.2022
Freies Schlagwort / Tag:speech command classification, power consumption, ARMv6, random forests, TensorFlow Lite, TreeLite, precision-over-energy
GND-Schlagwort:Raspberry Pi Zero WGND; Automatische SpracherkennungGND
Erste Seite:1
Letzte Seite:14
Seitenzahl:14
Fakultäten und Einrichtungen:Fakultät Gestaltung
Lizenz (Deutsch):Creative Commons - CC BY-SA - Namensnennung - Weitergabe unter gleichen Bedingungen 4.0 International
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.