ANOMALOUS SOUND DETECTION WITH TIMBRE SEPARATION

Methods, systems, and computer program products for detecting anomalous behavior include reconstructing a waveform of a target device from an input waveform using a target autoencoder. A waveform of unrelated sound events is reconstructed from the input waveform using an environmental autoencoder. T...

Full description

Saved in:
Bibliographic Details
Main Authors Vinayavekhin, Phongtharin, Inoue, Tadanobu, Tatsubori, Michiaki, Tachibana, Ryuki, Morikuni, Shu
Format Patent
LanguageEnglish
Published 11.08.2022
Subjects
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
MEASURING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
TESTING
TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES
TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR
Online AccessGet full text

Cover

More Information
Summary:Methods, systems, and computer program products for detecting anomalous behavior include reconstructing a waveform of a target device from an input waveform using a target autoencoder. A waveform of unrelated sound events is reconstructed from the input waveform using an environmental autoencoder. The input waveform is classified to determine that the input waveform is produced by anomalous behavior of the target device using a classifier, based on the reconstructed waveform of the target device and the reconstructed waveform of the unrelated sound events. An automatic response to the anomalous behavior is generated.
Bibliography:Application Number: US202117171259