Continuous utterance estimation apparatus, continuous utterance estimation method, and program

A sequential utterance estimation method comprising:

• generating, by processing circuitry of a sequential utterance estimation apparatus, a keyword detection result indicating a result of detecting an utterance of a predetermined keyword from an input voice;
• generating, by the processing circuitry of the sequential utterance estimation apparatus, a voice section detection result indicating a result of detecting a voice section from the input voice;
• generating, by the processing circuitry of the sequential utterance estimation apparatus, a sequential utterance detection result indicating that a sequential utterance has been made if the keyword detection result indicates that the keyword has been detected and if the voice section detection result indicates that the voice section has been detected;
• outputting, by the processing circuitry of the sequential utterance estimation apparatus, a predetermined response sound if the keyword detection result indicates that the keyword has been detected and if the sequential utterance detection result does not indicate that a sequential utterance has been detected;
• and
• outputting, as a target sound, by the processing circuitry of the sequential utterance estimation apparatus, the input voice delayed by a length of the response sound if the keyword detection result indicates that the keyword has been detected and if the sequential utterance detection result does not indicate that a sequential utterance has been detected, and output the input voice that is not delayed as the target sound if the keyword detection result indicates that the keyword has been detected and if the sequential utterance detection result indicates that a sequential utterance has been detected.

A non-transitory computer-readable recording medium on which a program recorded thereon for causing a computer to function as a sequential utterance estimation apparatus comprising:

• keyword detection circuitry configured to generate a keyword detection result indicating a result of detecting an utterance of a predetermined keyword from an input voice;
• voice detection circuitry configured to generate a voice section detection result indicating a result of detecting a voice section from the input voice;
• sequential utterance detection circuitry configured to generate a sequential utterance detection result indicating that a sequential utterance has been made if the keyword detection result indicates that the keyword has been detected, and if the voice section detection result indicates that the voice section has been detected;
• a response sound output circuitry configured to output a predetermined response sound if the keyword detection result indicates that the keyword has been detected and if the sequential utterance detection result does not indicate that a sequential utterance has been detected;
• and
• target sound output circuitry configured to output, as a target sound, the input voice delayed by a length of the response sound if the keyword detection result indicates that the keyword has been detected and if the sequential utterance detection result does not indicate that a sequential utterance has been detected, and output the input voice that is not delayed as the target sound if the keyword detection result indicates that the keyword has been detected and if the sequential utterance detection result indicates that a sequential utterance has been detected.