All assembly implementation of G.729 Annex B speech codec on a fixed point DSP

A lot of effort has been spent over the last few years in the development of digital speech coding methods and their subsequent standardization. Algorithms have evolved which provide good quality speech at sub 8 kbps bit rates although at a much higher computational expense. DSP processors have also improved with time providing specific signal processing functionalities aiding in easier codec implementations along with lower power consumption at higher clock speeds. Software development tools and compilers have also improved although they still do not work well in high volume, low cost systems. The cost of development tools may also be prohibitive for nonvendors and at times high level code conversion tools may not be present at all. This paper describes techniques and approaches commonly used to realize such systems where the codec implementation in all assembly is necessary. The specific codec implemented was International Telecommunication Union (ITU-T) G.729 Annex B. The techniques described in this paper are applicable to any other speech codec.