Speech Decoloration based on the Product-of-Filters Model

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Publication date: May 9, 2014

Dawen Liang, Daniel P. W. Ellis, Matthew Hoffman, Gautham Mysore

We present a single-channel speech decoloration method based on a recently proposed generative product-of-filters (PoF) model. We take a spectral approach and attempt to learn the magnitude response of the actual coloration filter, given only the degraded speech signal. Experiments on synthetic data demonstrate that the proposed method effectively captures both coarse and fine structure of the coloration filter. On real recordings, we find that simply subtracting the learned coloration filter from the log-spectra yields promising decoloration results.

Research Areas:  Adobe Research iconAI & Machine Learning Adobe Research iconAudio