Information processing device, information processing method, and program

1 . An information processing device comprising circuitry configured to

receive, by a microphone, an audio signal including a spreading code signal obtained by performing spread spectrum modulation on a spreading code, the audio signal being output from two speakers existing at known positions,

calculate a position of the microphone on a basis of an arrival time difference distance that is a difference between distances identified from an arrival time that is a time until the audio signals of the two speakers arrive at the microphone and are received, and

calculate a position of the microphone as an output layer by performing processing using a hidden layer including a neural network formed by machine learning on an input layer including the arrival time difference distance.

2 . The information processing device according to claim 1 , wherein

the circuitry is further configured to

calculate an arrival time until each of the audio signals of the two speakers arrives at the microphone, and

calculate, as the arrival time difference distance, a difference in distance between each of the two speakers and the microphone on a basis of an arrival time of each of the audio signals of the two speakers and a known position of the two speakers.

3 . The information processing device according to claim 2 , wherein

the circuitry is further configured to

calculate a cross-correlation between a spreading code signal in the audio signal received by the microphone and a spreading code signal of the audio signals output from the two speakers,

detect a time at which a peak occurs in the cross-correlation as the arrival time, and

calculate, as the arrival time difference distance, a difference in distance between the two speakers and the microphone based on the arrival time.

4 . The information processing device according to claim 3 , wherein

the circuitry is further configured to calculate the position of the microphone as an output layer by performing processing using a hidden layer including the neural network formed by machine learning on an input layer including the arrival time difference distance and a peak power ratio that is a ratio of power at a timing at which a peak occurs in the cross-correlation of audio signals output from the two speakers.

5 . The information processing device according to claim 4 , wherein the circuitry is further configured to

detect, as peak power, power at a time when an audio signal output from each of the two speakers at the peak is received by the microphone, and

calculate, as a peak power ratio, a ratio of peak powers of the audio signals output from the two speakers, the peak power being detected by the circuitry.

6 . The information processing device according to claim 5 , wherein

the circuitry is further configured to calculate the position of the microphone as the output layer by performing processing using the hidden layer on an input layer including the arrival time difference distance and the peak power ratio.

7 . The information processing device according to claim 4 , wherein

the circuitry is further configured to calculate the position of the microphone as an output layer by performing processing using a hidden layer including the neural network formed by machine learning on an input layer including the arrival time difference distance, the peak power ratio of audio signals output from the two speakers, and a peak power frequency component ratio that is a ratio of a peak power of a low-frequency component to a peak power of a high-frequency component of an audio signal output from each of the two speakers.

8 . The information processing device according to claim 7 , wherein the circuitry is further configured to

detect the peak power of a low-frequency component and the peak power of a high-frequency component of an audio signal output from each of the two speakers at the peak, and calculate a ratio of the peak power of the high-frequency component to the peak power of the low-frequency component as the peak power frequency component ratio.

9 . The information processing device according to claim 2 , wherein

the circuitry is further configured to

calculate a position of the speaker of the microphone in a direction perpendicular to an audio emission direction of the audio signal by the machine learning on a basis of an arrival time difference distance of the audio signals of the two speakers received by the microphone, and

calculate a position of the speaker of the microphone in the audio emission direction of the audio signal on a basis of an angle formed by directions of the two speakers with reference to the microphone.

10 . The information processing device according to claim 9 , wherein the circuitry is further configured to

detect angular velocity and acceleration of the microphone,

detect a posture of the information processing device on a basis of the angular velocity and the acceleration,

calculate an angle formed by directions of the two speakers with reference to the microphone on a basis of the posture of the information processing device, and

calculate a position of the speaker of the microphone in the audio emission direction of the audio signal on a basis of the calculated angle formed by directions of the two speakers with reference to the microphone.

11 . The information processing device according to claim 10 , wherein

the circuitry is further configured to calculate an angle formed by directions of the two speakers with reference to the microphone on a basis of a posture when the microphone turns itself toward each of the two speakers.

12 . The information processing device according to claim 11 , wherein

the circuitry is further configured to calculate a position of the speaker of the microphone in the audio emission direction of the audio signal from a relational expression of an inner product on a basis of an angle formed by directions of the two speakers with reference to the microphone.

13 . The information processing device according to claim 2 , further comprising

another microphone different from the microphone, wherein

the circuitry is further configured to

calculate a position of the speaker of the microphone in a direction perpendicular to an audio emission direction of the audio signal by machine learning on a basis of an arrival time difference distance of the audio signals of the two speakers received by the microphone, and

form simultaneous equations on a basis of the arrival time difference distance of the audio signals of the two speakers received by the microphone and the another microphone, and solve the simultaneous equations to calculate a position of the speaker of the microphone in the audio emission direction of the audio signal, an angle formed by directions connecting the microphone and the another microphone with respect to the audio emission direction of the audio signal of the speaker, and a distance between the microphone and the another microphone.

14 . The information processing device according to claim 2 , further comprising

another microphone different from the microphone, wherein

in a case where a distance between the microphone and the another microphone is known, the circuitry is further configured to form simultaneous equations on a basis of an arrival time difference distance of the audio signals of the two speakers, information on a known position of the speaker, and a known distance between the microphone and the another microphone that are received by the microphone and the another microphone, and solve the simultaneous equations to calculate a two-dimensional position of the microphone and an angle formed by a direction connecting the microphone and the another microphone with respect to an audio emission direction of the audio signal of the speaker.

15 . The information processing device according to claim 1 , wherein

the information processing device is a smartphone or a head mounted display (HMD).

16 . An information processing method comprising

receiving, by a microphone, an audio signal including a spreading code signal obtained by performing spread spectrum modulation on a spreading code, the audio signal being output from two speakers existing at known positions,

calculating a position of the microphone on a basis of an arrival time difference distance that is a difference between distances identified from an arrival time that is a time until the audio signals of the two speakers arrive at the microphone and are received, and

calculating a position of the microphone as an output layer by performing processing using a hidden layer including a neural network formed by machine learning on an input layer including the arrival time difference distance.

17 . A non-transitory computer-readable medium having embodied thereon a program, which when executed by a computer causes the computer to execute an information processing method, the method comprising

receiving, by a microphone, an audio signal including a spreading code signal obtained by performing spread spectrum modulation on a spreading code, the audio signal being output from two speakers existing at known positions,

calculating a position of the microphone on a basis of an arrival time difference distance that is a difference between distances identified from an arrival time that is a time until the audio signals of the two speakers arrive at the microphone and are received, and

calculating a position of the microphone as an output layer by performing processing using a hidden layer including a neural network formed by machine learning on an input layer including the arrival time difference distance.