Abstract. An architecture for achieving word recognition and incremental learning of new words in a language processing system is presented. The architecture is based on neural associative memories and hidden Markov models. The hidden Markov models generate subword-unit transcriptions of the spoken words and provide them as input to the associative memory module. The associative memory module is a network of binary autoand heteroassociative memories and responsible for combining words from subword-units. The basic version of the system is implemented for simple command sentences. Its performance is compared with the performance of the hidden Markov models.