MANAGEMENT LAYER FOR MULTIPLE INTELLIGENT PERSONAL ASSISTANT SERVICES

摘要

A step of performing voice recognition in a multi-device system comprises the steps of: receiving a first audio signal generated by a first microphone in response to a spoken expression and a second audio signal generated by a second microphone in response to a spoken expression; dividing the first audio signal into a first sequence of time segments; dividing the second audio signal into a second sequence of time segments; comparing a sound energy level associated with a first time segment of the first sequence with a sound energy level associated with a first time segment of the second sequence; selecting one of the first time segment of the first sequence and the first time segment of the second sequence as a first time segment of a voice recognition audio signal on the basis of the comparison; and performing voice recognition on the voice recognition audio signal.;COPYRIGHT KIPO 2018