| 摘要 |
A system comprising a processor (48, 60) that provides measurements of speec h distortion (50, 60) from samples of telephonic voice signals (10, 12) calculates and analyzes first and second derivatives of the processing sampl es of natural speech provided through telephony system (10, 12), to detect and determine the incidence of change in the voice waveform that would have not been made by human articulation. Statistical analysis is performed of both t he first and second discrete derivatives to detect speech distortion by looking at the distribution of the signals. For example, the kurtosis of the signals is analyzed as well as the number of times these values exceed a predetermin ed threshold.
|
