A Temporal Model of Aural Frequency Discrimination

The importance of temporal information versus place information in frequency analysis by the ear is a continuing controversy. This dissertation developes a temporal model which simulates human frequency discrimination. The model gives guantitative measures of performance for the discrimination of sinusoids in white gaussian noise. The model simulates human frequency discrimination performance as a function of frequency and signal-to-noise ratio. The model's predictions are based on the temporal intervals between the positive axis crossings of the stimulus. The histograms of these temporal intervals were used as the underlying distributions from which indices of discriminability were calculated. Human freguency discrimination data was obtained for five observers as a function of frequency and signal-to-noise ratio. The data were analysed using the method of Group-operating-characteristic (GOC) Analysis. This method of analysis statistically removes unique noise from data. The unique noise was removed by summing observers' ratings for identical stimuli. This method of analysis gave human frequency discrimination data with less unigue noise than any existing frequency data. The human data were used for evaluating the model. The GOC Analysis was also used to study the improvement in d' as a function of stimulus replications and signal-to-noise ratio. The model was a good fit to the human data at 250 Hz, for two signal-to-noise ratios. The model did not fit the data at 1000 Hz or 5000 Hz. There was some evidence of a transition occuring at 1000 Hz. This investigation supported the idea that human frequency discrimination relies on a temporal mechanism at low frequencies with a transition to some other mechanism at about lO00 Hz.