Speech Signal Processing

Consistent Wiener Filtering

- Audio Examples -

While a classical Wiener filter changes only the magnitudes in the STFT domain,separately for each time-frequency point, the consistent Wiener filter takes the relationship between STFT coefficients across time and frequency into account, which modifies both the magnitude and the phase of the noisy observation to obtain the separated speech.

More details and code can be found here.

Here we present some listening examples for real-world signals from SiSEC 2010. For each noise condition we present the noisy mixture, the result obtained with a conventional Wiener filter, and the outcome of the consistent Wiener filter.

Reference

[LRV13] J. Le Roux and E. Vincent, “Consistent Wiener filtering for audio source separation,” IEEE Signal Processing Letters, vol. 20, no. 3, pp. 217–220, Mar. 2013.


Public square at 0 dB SNR:



Noisy Mixture
Conventional Wiener Filter
Consistent Wiener Filter

Cafeteria at 0 dB SNR:

Noisy Mixture
Conventional Wiener Filter
Consistent Wiener Filter