A mixed sinusoidally excited linear prediction coder at 4 kb/s and below

Abstract

There is currently a great deal of interest in the development of speech coding algorithms capable of delivering toll quality at 4 kb/s and below. For synthesizing high quality speech, accurate representation of the voiced portions of speech is essential. For bit rates of 4 kb/s and below, conventional code excited linear prediction (CELP) may likely not provide the appropriate degree of periodicity. It has been shown that good quality low bit rate speech coding can be obtained by frequency domain techniques such as sinusoidal transform coding (STC), multi-band excitation (MBE), mixed excitation linear prediction (MELP), and multi-band LPC (MB-LPC) vocoders. In this paper, a speech coding algorithm based on an improved version of MB-LPC is presented. Main features of this algorithm include a multi-stage time/frequency pitch estimation and an improved mixed voicing representation. An efficient quantization scheme for the spectral amplitudes of the excitation, called formant weighted vector quantization, is also used. This improved coder, called mixed sinusoidally excited linear prediction (MSELP), yields an unquantized model with speech quality better than the 32 kb/s AD-PCM quality. Initial efforts towards a fully quantized 4 kb/s coder, although not yet successful in achieving the toll quality goal, have produced good output speech quality.