No description
- Python 100%
| test | ||
| denoise_ogs.py | ||
| denoise_sub.py | ||
| README.md | ||
Speech enhancement (noise reduction)
Papers
Statistical speech enhancement techniques:
| Paper | Notes |
|---|---|
| Ephraim, Y., & Malah, D. (1984). Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Transactions on acoustics, speech, and signal processing, 32(6), 1109-1121. ResearchGate | Introduces Decision-Directed estimation of a-priori SNR (\xi)Introduces MMSE-LSA gain function |
| Ephraim, Y., & Malah, D. (1985). Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE transactions on acoustics, speech, and signal processing, 33(2), 443-445. ResearchGate / PDF | Introduces MMSE-LSA gain function |
| Malah, D., Cox, R. V., & Accardi, A. J. (1999, March). Tracking speech-presence uncertainty to improve speech enhancement in non-stationary noise environments. In 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No. 99CH36258) (Vol. 2, pp. 789-792). IEEE. ResearchGate | Adds H_0/H_1 to MMSE-LSA gain |
| Cohen, I., & Berdugo, B. (2001). Speech enhancement for non-stationary noise environments. Signal processing, 81(11), 2403-2418. PDF | Introduce OM-LSA gain Introduce MCRA noise estimation |
| Martin, R., & Breithaupt, C. (2003, September). Speech enhancement in the DFT domain using Laplacian speech priors. In Proc. IWAENC (Vol. 3, pp. 87-90). PDF | Introduce Laplacian speech model |
| Cohen, I. (2005). Speech enhancement using super-Gaussian speech models and noncausal a priori SNR estimation. Speech communication, 47(3), 336-350. PDF | Use Laplacian & Gamma speech model to improve noise PSD estimation |
| Abramson, A., & Cohen, I. (2007). Simultaneous detection and estimation approach for speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing, 15(8), 2348-2359. PDF | |
| Rashidi-nejad, M., Abutalebi, H. R., & Tadaion, A. A. (2010, December). Speech enhancement using an Improved MMSE estimator with Laplacian prior. In 2010 5th International Symposium on Telecommunications (pp. 889-894). IEEE. ResearchGate | Improves over the OM-LSA gain |
Noise density estimation:
| Paper | Notes |
|---|---|
| Hendriks, R. C., Heusdens, R., & Jensen, J. (2010, March). MMSE based noise PSD tracking with low complexity. In 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 4266-4269). IEEE. PDF | Good overall performance, relatively simple PSD estimation |
| Gerkmann, T., & Hendriks, R. C. (2011). Unbiased MMSE-based noise power estimation with low complexity and low tracking delay. IEEE Transactions on Audio, Speech, and Language Processing, 20(4), 1383-1393. PDF | Improves on Hendriks et al, 2010 |
| Gerkmann, T., & Hendriks, R. C. (2012, March). Improved MMSE-based noise PSD tracking using temporal cepstrum smoothing. In 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 105-108). IEEE. PDF | Improves on Hendriks et al, 2010 |
| Taghia, J., Taghia, J., Mohammadiha, N., Sang, J., Bouse, V., & Martin, R. (2011, May). An evaluation of noise power spectral density estimation algorithms in adverse acoustic environments. In 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4640-4643). IEEE. PDF | |
| Sunnydayal, V., Sivaprasad, N., & Kumar, T. K. (2014). A survey on statistical based single channel speech enhancement techniques. International Journal of Intelligent Systems and Applications, 6(12), 69. PDF | |
| Li, X., Girin, L., Gannot, S., & Horaud, R. (2016, March). Non-stationary noise power spectral density estimation based on regional statistics. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 181-185). IEEE. PDF | |
| Roy, S. K., & Paliwal, K. K. (2021). A noise PSD estimation algorithm using derivative-based high-pass filter in non-stationary noise conditions. EURASIP Journal on Audio, Speech, and Music Processing, 2021(1), 1-18. HTML |