Image capturing apparatus, information processing method and storage medium for estimating a position of a sound source

摘要

An image capturing apparatus according to exemplary embodiments of the present invention includes a viewfinder and a display, switches between a display mode for displaying an image on the viewfinder, and a display mode for displaying an image on the display, sets processing of speech input to a mode for close-talking, when an image is displayed on the viewfinder, sets processing of speech input to a mode for non-close-talking, when an image is displayed on the display, and inputs by speech a control command that has been set in advance according to a mode of speech input that has been set.

主权项

1. An image capturing apparatus including a viewfinder, a display, and at least one microphone, the image capturing apparatus comprising:
a switching unit configured to switch a display mode for displaying an image on the viewfinder and a display mode for displaying an image on the display; a setting unit configured to set, in response to the display mode for displaying an image on the viewfinder being set, an input level of the at least one microphone to V1 for capturing sounds uttered from a user by estimating that the user's mouth is located at a position close to the at least one microphone, and to set, in response to the display mode for displaying an image on the display being set, the input level of the at least one microphone to V2 for capturing sounds uttered from the user by estimating that the user's mouth is located at a position a little apart from the at least one microphone; and an input unit configured to input by speech a control command based on the set input level, wherein a value of V2 is larger than a value of V1.