摘要 |
PROBLEM TO BE SOLVED: To prevent voice from being misrecognized owing to noise that a robot generates. SOLUTION: A voice signal inputted to a microphone is converted by an AD conversion part 41 into a digital signal, which is outputted to a voice section detection part 47 and a feature extraction part 42. The voice section detection part 47 decides that the signal is not a voice section while an actuator nearby the microphone is in operation according to state recognition information and attitude transition information and then cancels voice recognition processing and varies the value of a threshold for determining the start of a voice section according to the contents of the operation and state. When the robot is walking, the feature extraction part 42 extracts features by using voice data from which pulsative grounding noise generated during the walk is removed through frame removable, filtering, etc.
|