One of the main limitations of the people with hearing impairment is directly related to their difficulty interacting with others, either verbally or through auxiliary systems based on voice and audio. This paper presents the development of an integrated system of hardware and software for automatic fingerspelling sign language used by people with this type of disability. The hardware system comprises a glove which has a set of wireless sensors that capture a series of signals generated by the hand gestures, and a adaptive model based on the principles of neural computation, that allows recognition of a particular dactilologic language. Results from the integrated system showed great effectiveness in recognizing vowels from the dactilologic Spanish language. This recognition was influenced by the dimensionality reduction made by the neural model of the input signals representing movements, and the sensitivity factor that sets the limit between recognition and learning.