Erroneous detection determination device, erroneous detection determination method, and storage medium storing erroneous detection determination program

An erroneous detection determination device comprising:

• a processor configured to execute
• acquiring, from each of a plurality of microphones, a plurality of audio signals relating to ambient sound including sound from a sound source in a certain direction,
• acquiring a recognition result including voice activity information indicating the inclusion of a voice activity relating to at least one of the plurality of audio signals,
• calculating, on the basis of the signal of respective unit time of the plurality of audio signals and the certain direction, a speech arrival rate representing the proportion of the sound from the certain direction to the ambient sound in each of the unit times,
• determining, on the basis of the recognition result and the speech arrival rate, whether or not the voice activity information is the result of erroneous detection, and
• outputting the result of determination.

A storage medium storing an erroneous detection determination program that causes a computer to execute:

• acquiring, from each of a plurality of microphones, a plurality of audio signals relating to ambient sound including sound from a sound source in a certain direction;
• acquiring a recognition result including voice activity information indicating the inclusion of a voice activity relating to at least one of the plurality of audio signals;
• calculating, on the basis of the signal of respective unit time of the plurality of audio signals and the certain direction, a speech arrival rate representing the proportion of the sound from the certain direction to the ambient sound in each of the unit times;
• determining, on the basis of the recognition result and the speech arrival rate, whether or not the voice activity information is the result of erroneous detection;
• and
• outputting the result of determination.

An erroneous detection determination method executed by a computer, the erroneous detection determination method comprising:

• acquiring, from each of a plurality of microphones, a plurality of audio signals relating to ambient sound including sound from a sound source in a certain direction;
• acquiring a recognition result including voice activity information indicating the inclusion of a voice activity relating to at least one of the plurality of audio signals;
• calculating, on the basis of the signal of respective unit time of the plurality of audio signals and the certain direction, a speech arrival rate representing the proportion of the sound from the certain direction to the ambient sound in each of the unit times;
• determining, on the basis of the recognition result and the speech arrival rate, whether or not the voice activity information is the result of erroneous detection;
• and
• outputting the result of determination.