| 摘要 |
An arrangement for automatically recognizing signal sequences such as speech and/or music signals, particularly useful for statistical evaluation of the frequency of play of music titles, commercial advertising spots, or verbal materials, etc. One envelope signal is generated from each preset signal sequence (e.g., music title) and time segments of the envelope signals are stored. An envelope signal is also generated from a signal sequence that is to be examined. Time segments of the envelope signal of the signal sequence to be examined are continually compared with the stored segments of the envelope signals of the preset signal sequences. When a preset degree of concordance is exceeded, a recognition signal is generated. |
