The effects of parameter modifications imposed by hardware con(cid:173) straints on a self-organizing feature map algorithm were examined. Performance was measured by the error rate of a speech recogni(cid:173) tion system which included this algorithm as part of the front-end processing. System parameters which were varied included weight (connection strength) quantization, adap tation quantization, dis(cid:173) tance measures and circuit approximations which include device characteristics and process variability. Experiments using the TI isolated word database for 16 speakers demonstrated degradation in performance when weight quantization fell below 8 bits. The com(cid:173) petitive nature of the algorithm rela..xes constraints on uniformity and linearity which makes it an excellent candidate for a fully ana(cid:173) log circuit implementation.

The effects of parameter modifications imposed by hardware constraints on a self-organizing feature map algorithm were examined. Performance was measured by the error rate of a speech recognition system which included this algorithm as part of the front-end processing. System parameters which were varied included weight (connection strength) quantization, adap tation quantization, distance measures and circuit approximations which include device characteristics and process variability. Experiments using the TI isolated word database for 16 speakers demonstrated degradation in performance when weight quantization fell below 8 bits. The competitive nature of the algorithm rela..xes constraints on uniformity and linearity which makes it an excellent candidate for a fully analog circuit implementation. Prototype circuits have been fabricated and characterized following the constraints established through the simulation efforts. 1 Introduction The self-organizing feature map algorithm developed by Kohonen [Kohonen, 1988] readily lends itself to the task of vector quantization for use in such areas as speech recognition.

The effects of parameter modifications imposed by hardware constraints on a self-organizing feature map algorithm were examined. Performance was measured by the error rate of a speech recognition system which included this algorithm as part of the front-end processing. System parameters which were varied included weight (connection strength) quantization, adap tation quantization, distance measures and circuit approximations which include device characteristics and process variability. Experiments using the TI isolated word database for 16 speakers demonstrated degradation in performance when weight quantization fell below 8 bits. The competitive nature of the algorithm rela..xes constraints on uniformity and linearity which makes it an excellent candidate for a fully analog circuit implementation. Prototype circuits have been fabricated and characterized following the constraints established through the simulation efforts. 1 Introduction The self-organizing feature map algorithm developed by Kohonen [Kohonen, 1988] readily lends itself to the task of vector quantization for use in such areas as speech recognition.

In fact, performance was often improved over the original learning rule.