Noise reduction for human speech signals by local projections in embedding spaces

A local projective noise-reduction scheme, originally developed for low-dimensional deterministic stationary signals, is successfully applied to human speech. This is possible by exploiting properties of the speech signal which mimic structure exhibited by deterministic chaotic systems. In high-dimensional embedding spaces, the strong nonstationarity is resolved as a sequence of different dynamical regimes of moderate complexity. This filtering technique does not make use of the spectral contents of the signal and is superior to the Ephraim-Malah adaptive filter.