| 摘要 |
A method of extracting abnormal sound components from a sound is provided to make noise removable or make only abnormal sound extractable by extracting abnormal sound or removing noise individually from the steady component, white noise and non-steady component having non-steady property. A method of extracting abnormal sound components from a sound comprises the steps of inputting NG signal and OK signal, the NG signal containing an abnormal sound and the OK signal not containing the abnormal sound and containing noise that is contained in the NG signal, separating the NG signal and the OK signal each into a steady component having steady property, white noise and a non-steady component having non-steady property(2,3), and extracting abnormal sound or removing noise individually from the steady component, white noise and non-steady component having non-steady property(4,5).
|
