Real-time Detection of MEMS Microphone Array Failure Modes for Embedded Microprocessors

Stanford-Jason A. Real-time Detection of MEMS Microphone Array Failure Modes for Embedded Microprocessors. In: AES Convention 143. Audio Engineering Society; 2017. Paper 402. Available from: https://aes.org/publications/elibrary-page/?id=19350

@inproceedings{StanfordJason2017_19350,
  author = {Stanford-Jason, Andrew},
  title = {{Real-time Detection of MEMS Microphone Array Failure Modes for Embedded Microprocessors}},
  booktitle = {AES Convention 143},
  note = {Paper 402},
  year = {2017},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19350}
}

TY  - CPAPER
TI  - Real-time Detection of MEMS Microphone Array Failure Modes for Embedded Microprocessors
AU  - Stanford-Jason, Andrew
T2  - AES Convention 143
M1  - Paper 402
PY  - 2017
DA  - 2017/10/06
UR  - https://aes.org/publications/elibrary-page/?id=19350
PB  - Audio Engineering Society
LA  - en
AB  - In this paper we describe an online system for real-time detection of common failure modes of arrays of MEMS microphones. We describe a system with a specific focus on reduced computational complexity for application in embedded microprocessors. The system detects deviations is long-term spectral content and microphone covariance to identify failures while being robust to the false negatives inherent in a passively driven online system. Data collected from real compromised microphones show that we can achieve high rates of failure detection.
ER  -