Multicore DSP

17Adaptive filter implementation

CHAPTER MENU

1. 17.1 Introduction
2. 17.2 Mean square error
3. 17.3 Least mean square
4. 17.4 Implementation of an adaptive filter using the LMS algorithm
5. 17.5 Implementation using linear assembly
6. 17.6 Implementation in C language with compiler switches
7. 17.7 Laboratory experiment
8. 17.8 Conclusion
9. References

17.1 Introduction

Adaptive filters differ from other filters, such as finite impulse response (FIR) and infinite impulse response (IIR) filters, in the sense that the filter coefficients are not fixed and are determined by some desired specifications. In adaptive filters, the specifications are not known and change with time. Applications of adaptive filters are numerous and include process control, medical instrumentation, speech processing, echo and noise cancellation and channel equalisation.

The general procedure for constructing an adaptive filter is firstly to choose a FIR or IIR filter, and secondly to have a mechanism or algorithm to optimally adjust the FIR or IIR coefficients (see Figure 17.1) [1–3].

Figure 17.1 Basic block diagram of an adaptive filter.

The real challenge for designing an adaptive filter resides with the adaptive algorithm. The latter needs to be practical to implement, adapt the filter coefficients quickly and provide the desired performance.

How is the performance measured? The main criterion that provides a good ...