语音信号去混响是语音降噪的一种方法，本文现将至2020年7月经典的算法总结如下，按时间顺序排序。
算法目录
1. Two-stage algorithm by DeLiang Wang’s Group
方法概述
Inverse filter Arrangements
论文与代码
Mingyang Wu and DeLiang Wang, “A two-stage algorithm for one-microphone reverberant speech enhancement,” in IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 3, pp. 774-784, May 2006, doi: 10.1109/TSA.2005.858066.
2. About This Dereverberation Business: A Method for Extracting Reverberation from Audio Signals
专利与代码:
Soulodre, Gilbert A. 2010. “About this dereverberation business: A method for extracting reverberation from audio signals.” In Audio Engineering Society Convention 129. Audio Engineering Society.
3. WPE
论文与代码
Yoshioka, Takuya, and Tomohiro Nakatani. “Generalization of multi-channel linear prediction methods for blind MIMO impulse response shortening.” IEEE Transactions on Audio, Speech, and Language Processing 20.10 (2012): 2707-2720.
4. Exemplar-based sparse representations by Deepak Baby
论文与代码:
Deepak Baby and Hugo Van hamme. Supervised Speech Dereverberation in Noisy Environments using Exemplar-based Sparse Representations. In Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on, Shanghai, China, March 2016.
5. SPENDRED (SPeech ENhancement and DeREverberation by Doire)
论文与代码:
C. S. J. Doire, D. M. Brookes, P. A. Naylor, C. M. Hicks, D. Betts, M. A. Dmour, and S. H. Jensen. Single-channel online enhancement of speech corrupted by reverberation and noise. IEEE Trans. Audio, Speech, Language Processing, 25 (3): 572-587, Mar. 2017. doi: 10.1109/TASLP.2016.2641904.
6. DNN_WPE
论文与代码：
Kinoshita, Keisuke et al. “Neural Network-Based Spectrum Estimation for Online WPE Dereverberation.” INTERSPEECH (2017).