Audio signal processing device, imaging device, audio signal processing method, program, and recording medium

摘要

There is provided an audio signal processing device including a feature amount extraction unit configured to extract, from an audio signal obtained by a sound collection unit, a feature amount that indicates a pulsed operation sound generated from a sound generation unit provided in a same housing as the sound collection unit, and a noise determination unit configured to determine whether or not the operation sound is included in the audio signal based on the feature amount.

主权项

1. An audio signal processing device comprising:
a feature amount extraction unit configured to extract, from an audio signal obtained by a sound collection unit, a feature amount that indicates a pulsed operation sound generated from a sound generation unit provided in a same housing as the sound collection unit, wherein the feature amount extraction unit is further configured to:
extract a first feature amount that indicates a pulse component of the pulsed operation sound and a second feature amount that indicates a reverberation component of the pulsed operation sound as the feature amount, andextract, as the feature amount, a third feature amount including some or all of an RMS of the audio signal, a value of change of the RMS, a changed amplitude value of a narrow-band signal that indicates the reverberation component of the pulsed operation sound and a value of change of a number of zero-crossing times of the narrow-band signal; and a noise determination unit configured to determine whether or not the pulsed operation sound is included in the audio signal based on the first, second and third feature amounts.