US 11,915,681 B2
Information processing device and control method
Akihiro Ito, Tokyo (JP); and Satoru Furuta, Tokyo (JP)
Assigned to MITSUBISHI ELECTRIC CORPORATION, Tokyo (JP)
Filed by Mitsubishi Electric Corporation, Tokyo (JP)
Filed on Jan. 19, 2022, as Appl. No. 17/579,286.
Application 17/579,286 is a continuation of application No. PCT/JP2019/029983, filed on Jul. 31, 2019.
Prior Publication US 2022/0139367 A1, May 5, 2022
Int. Cl. G10K 11/34 (2006.01); G10L 25/84 (2013.01); H04R 1/40 (2006.01); H04R 3/00 (2006.01)
CPC G10K 11/34 (2013.01) [G10L 25/84 (2013.01); H04R 1/406 (2013.01); H04R 3/00 (2013.01)] 4 Claims
OG exemplary drawing
 
1. An information processing device comprising:
a signal acquiring circuitry to acquire a voice signal of an object person outputted from a plurality of microphones;
a speech level acquiring circuitry to acquire at least one of a first speech level indicating a degree of speech of the obstructor in a state in which an angle between the direction in which the voice of the object person is inputted to the plurality of microphones and a direction in which the voice of the obstructor is inputted to the plurality of microphones is less than or equal to a first threshold value and a second speech level indicating the degree of the speech of the obstructor in a state in which the angle is greater than the first threshold value from a speech level generation device;
a speech judging circuitry to judge whether the obstructor is speaking while obstructing the speech of the object person or not based on a speech level judgment threshold value as a predetermined threshold value and at least one of the first speech level and the second speech level; and
a controlling circuitry to acquire at least one of noise level information indicating a noise level of noise and first information as information indicating a result of the judgment, and change a beam width as a width of a beam corresponding to an angular range of acquired sound, centering at the beam representing a direction in which voice of the object person is inputted to the plurality of microphones, and dead zone formation intensity as a degree of suppressing at least one of the noise and voice of the obstructor inputted to the plurality of microphones based on at least one of the noise level information and the first information.