This paper presents a method of controlling redundant manipulators by spoken language commands consisting of fuzzy linguistic information. The present system introduces the fuzzy-neurocontrol paradigm to the contemporary speech controlled robotic systems, which are based on the on-off control paradigm. The system is sensitive to the action activation commands, action modification commands, and action repetition commands of the human-robot conversation carried out by practical dialogues. Credibility of the proposed system is experimentally proven by controlling a manipulator with seven degrees-of-freedom by fuzzy linguistic information enriched spoken language commands to perform an assembling task.