Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

An embedded system for acoustic pattern recognition

 
: Tschöpe, Constanze; Duckhorn, Frank; Richter, Christian; Blüthgen, Peter; Wolff, Matthias

:

Institute of Electrical and Electronics Engineers -IEEE-:
IEEE Sensors 2017. Conference Proceedings : October 29 - November 1, 2017, Glasgow, Scotland, UK
Piscataway, NJ: IEEE, 2017
ISBN: 978-1-5090-1012-7
ISBN: 978-1-5090-1013-4
ISBN: 978-1-5386-4056-2
pp.1512-1514
Sensors Conference <2017, Glasgow>
English
Conference Paper
Fraunhofer IKTS ()
hardware; sensor signal processing; pattern recognition; FPGA; DSP

Abstract
We present a miniaturized universal hardware module for acoustic pattern recognition in various types of multichannel sensor signals. The module implements a configurable signal analysis (signal transforms, filter banks, statistical transforms) and GMM-HMM recognizer. The main hardware components are a XC7A75T FPGA performing almost all the computations, a TMS320C6746 digital signal processor organizing the data flow and executing the automata search (decoding), 3x1 GiBit DDR2 memory and 4 GiBit flash memory. The module can be plugged into a host device and be connected to signal acquisition hardware. It can process input signals with up to approx. 250 kHz bandwidth for continuous input and up to approx. 3 MHz for burst input.

: http://publica.fraunhofer.de/documents/N-484779.html