Sound analysis apparatus for detecting sound sources

A sound analysis system comprising:

• a processor configured to act as:
• a plurality of sound acquiring sections that acquires a sound, the plurality of sound sections being vertically separated from each other by a predetermined distance;
• a distinguishing section that distinguishes whether the sound acquired by the sound acquiring sections is a spoken voice of a wearer or a spoken voice of another person;
• a phase difference deriving section that derives a relationship between a frequency and a phase difference with respect to the sound acquired by the plurality of sound acquiring sections, and derives a distance between the wearer and the other person on a basis of information relating to the sound acquired by the sound acquiring sections;
• a dispersion deriving section that derives a dispersion that is a level of irregularity of the phase difference derived by the phase difference deriving section;
• and
• a distance deriving section that derives the distance between the wearer and the other person using a first dispersion that is derived by the dispersion deriving section in a case where the sound is distinguished as the spoken voice of the other person and a second dispersion that is derived by the dispersion deriving section in a case where the sound is distinguished as the spoken voice of the wearer.

A non-transitory computer readable medium storing a program causing a computer to achieve functions, the functions comprising:

• obtaining information relating to a sound acquired by a plurality of sound acquiring sections that acquires the sound and distinguishes a spoken voice of a wearer from a spoken voice of another person, the plurality of sound acquiring sections being vertically separated from each other by a predetermined distance;
• deriving a relationship between a frequency and a phase difference with respect to the sound acquired by the plurality of sound acquiring sections;
• deriving a dispersion that is a level of irregularity of the derived phase difference;
• and
• deriving a distance between the wearer and the other person on a basis of the information relating to the sound acquired by the sound acquiring sections, and using:
• a first dispersion that is derived in a case where the sound is distinguished as the spoken voice of the other person;
• and a second dispersion that is derived in a case where the sound is distinguished as the spoken voice of the wearer.