| 摘要 |
<p>Sound-generating processes are classified using at least one sensor for detecting sound signals caused by the sound-generating processes. A storage stores a reference model which has statistical distribution parameters for predetermined characteristics of a sound signal. An adaptation unit extracts the characteristic from the detected sound signals of the processes and calculates a similarity between the sound signals detected based on the extracted characteristics for grouping the processes into various process clusters having sound signals that are similar to each other. The adaptation unit adapts the stored reference model as a function of the statistical distribution parameters of those processes in a process cluster having the maximum number of processes, then a classification unit classifies the sound-generating processes based on the adapted model.</p> |
