Single Channel Denoising

Module contents

Single Channel Noise Reduction

Collection of single channel noise reduction (SCNR) algorithms for speech:

• Spectral Subtraction [1]

• Subspace Approach [2]

• Iterative Wiener Filtering [3]

At this repository, a deep learning approach in Python can be found.

References

[1]

M. Berouti, R. Schwartz, and J. Makhoul, Enhancement of speech corrupted by acoustic noise, ICASSP ‘79. IEEE International Conference on Acoustics, Speech, and Signal Processing, 1979, pp. 208-211.

[2]

Y. Ephraim and H. L. Van Trees, A signal subspace approach for speech enhancement, IEEE Transactions on Speech and Audio Processing, vol. 3, no. 4, pp. 251-266, Jul 1995.

[3]

J. Lim and A. Oppenheim, All-Pole Modeling of Degraded Speech, IEEE Transactions on Acoustics, Speech, and Signal Processing 26.3 (1978): 197-210.

Algorithms

• pyroomacoustics.denoise.spectral_subtraction module
  • SpectralSub
    • SpectralSub.compute_gain_filter()
  • apply_spectral_sub()
• pyroomacoustics.denoise.subspace module
  • Subspace
    • Subspace.apply()
    • Subspace.compute_signal_projection()
    • Subspace.update_cov_matrices()
  • apply_subspace()
• pyroomacoustics.denoise.iterative_wiener module
  • IterativeWiener
    • IterativeWiener.compute_filtered_output()
  • apply_iterative_wiener()
  • compute_speech_psd()
  • compute_squared_gain()
  • compute_wiener_filter()