In Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. Paper Code abstract bibtex
While an exact stationarization of a process with a given spec- trum magnitude can be obtained via a complete randomiza- tion of the spectrum phase (``surrogates'' technique), we pro- pose here a softened version in which the degree of stationar- ization can be controlled by a perturbation of the actual phase. A basic theory for such ``transitional surrogates'' is first dis- cussed, with emphasis on two effective constructions based on either white Gaussian noise or random walks. Some typi- cal examples are considered for illustration, and performance evaluations are provided for supporting the usefulness of the approach in the context of stationarity testing.