The author considers the problem of coding the spectral amplitudes of a sinusoidal transform coding (STC) vocoder operating at 2400 b/s, which was previously considered by R.J. McAulay and T.F. Quatieri (1987). Differential pulse code modulation (DPCM) coding of spectral amplitudes in vocoders can cause formant clipping because of positive slope overload. The author presents a modified DPCM coder that prevents positive slope overload by anticipating large spectral peaks. When the vocoder is used on speech taken from a standard telephone set, a time-varying distortion of the low-end frequencies is observed. When the modified DPCM coder is applied to the telephone-set speech, its success was obvious. The time-varying distortion of the low-end frequencies is eliminated. Performance of the STC vocoder on the telephone-set speech is essentially identical to its performance on flat-frequency-response speech.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Read full abstract