Back to Search
Start Over
An embedded system for acoustic pattern recognition
- Source :
- 2017 IEEE SENSORS.
- Publication Year :
- 2017
- Publisher :
- IEEE, 2017.
-
Abstract
- We present a miniaturized universal hardware module for acoustic pattern recognition in various types of multichannel sensor signals. The module implements configurable signal analysis (signal transforms, filter banks, statistical transforms) and a 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), 3×1 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.
- Subjects :
- Digital signal processor
Signal processing
Computer science
business.industry
010401 analytical chemistry
Bandwidth (signal processing)
Process (computing)
Pattern recognition
01 natural sciences
Signal
Flash memory
0104 chemical sciences
Filter (video)
Pattern recognition (psychology)
Artificial intelligence
business
Field-programmable gate array
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2017 IEEE SENSORS
- Accession number :
- edsair.doi...........42a37a1a973bf55d9d6bfd40fa22dc70