A new AR model based speech enhancement approach within variational Bayesian framework

作者：Huang Qinghua^*; Yang Jie; Xue Yunfeng

来源：Chinese Journal of Electronics, 2007, 16(3): 499-502.

• speech enhancement
• autoregressive model
• variational Bayesian learning
• variational Kalman smoother

A new model-based speech enhancement algorithm by variational Bayesian learning was proposed in this paper. Autoregressive process was used to model speech signal and its order was determined automatically. Clean speech signal could be estimated using a variational Kalman smoother. Moreover, overfitting was avoided in the learning of model parameter and model structure. Experimental results compared with Kalman filter-based enhancement and spectral subtraction methods demonstrate the performance of our algorithm.

• 出版日期2007-7
• 单位上海交通大学