摘要 |
PURPOSE:To perform an input level adjustment between frames against the signal which conducts a frame unit processing. CONSTITUTION:Inputted voice signals are converted into digital signals by an A/D converter 4, compressed in a DSP section 5 and recorded in a recording medium 10. When inputted signal data equivalent to one frame are accumulated, the section 5 retrieves a maximum value of segment data and computes the energy, predicts the maximum value of the data of a next segment using a fuzzy inference, conducts a gain adjustment value prediction and controls the gain of the analog voice signals inputted to the converter 4 to the predicted gain adjustment value. |