Short Term Memory Demands in Processing Synthetic Speech

The purpose of the present experiment was to investigate the demands placed on the short term memory system by synthetic speech. We compared performance in a typical auditory short term memory task as a function of whether the items were presented by a human voice or by a text-to-speech computer voice generator. Immediate serial recall of digit strings was significantly poorer when presented by synthetic speech than when presented by natural speech. The results are consistent with the idea that comprehension of synthetic speech imposes increased resource demands on the short term memory system.