Fundamental frequency estimation based on instantaneous frequency amplitude spectrum

This paper describes a technique for estimating fundamental frequency of speech based on instantaneous frequency (IF). In the technique, fundamental frequency of a signal is obtained by evaluating its IF amplitude spectrum. We define a measure which represents how clearly the harmonic structure is shown in the IF amplitude spectrum. This harmonicity measure is used to select an optimal frequency band on which the IF amplitude spectrum is evaluated. We show the results of fundamental frequency estimation experiments using a speech database which contains 14 male and 14 female speakers' utterances. It is seen that the proposed technique can decrease gross errors substantially and obtain better performance than the conventional method based on the IF amplitude spectrum.