To test predictions of a forward modeling framework for spoken language processing, we characterized effects of context speech rate on the real-time interpretation of indefinite noun phrases using the visual world paradigm. The speech rate of sentence material distal to the onset of the noun phrase was manipulated such that the segments surrounding the determiner "a" in singular noun phrases had a faster speech rate than the surrounding context and the segments surrounding the onset of plural noun phrases had a relatively slow rate. These manipulations caused listeners to fail to perceive acoustically present determiners and to falsely perceive determiners not present in the signal. Crucially, fixations to singular and plural target pictures revealed effects of distal speech rate during the real-time processing of target expressions, strongly suggesting a locus in perceptual expectations. These results set the stage for quantitative tests of forward models of spoken language processing.