Speech Enhancement Based on Nonparametric Bayesian Method
- 数学科学－已发表论文 
提出一种基于非参数贝叶斯理论的语音增强算法,在稀疏表示的框架下,把字典学习、稀疏系数表示和噪声方差估计融合成一个贝叶斯后验估计的过程,并利用Sp; ike-Slab先验加强稀疏性.首先,将带噪语音分解为干净语音、高斯噪声和残余噪声3个子信号,分别对该3种子信号采用不同的先验概率模型表达,接着; 采用马尔科夫链-蒙特卡洛算法计算出3个模型中每个参数对应的后验概率,最后基于稀疏表示的框架重构出干净语音.实验数据使用NOIZEUS语音库,采用; PESQ和SegSNR作为质量评价指标,分别在信噪比为0,5和10; dB的高斯白噪声、火车噪声和街道噪声上验证了其可行性,并与多种常用语音增强方法进行对比,发现其在低信噪比非平稳噪声情况下的增强效果更为理想.A new speech enhancement strategy is proposed by utilizing a; nonparametric Bayesian method with Spike-Slab priori (NBSP).As a sparse; representation framework,the dictionary learning,sparse coefficients; representation and noise variance estimation are replaced by a single; procedure of Bayesian posterior estimation.First,the noisy speech is; divided into clean speech,Gaussian noise and rest noise.Then,each part; is modeled with a certain priori distribution.Finally,upon the adoption; of Markov Chain Monte Carlo sampling algorithm,the posterior; distribution can be obtained,as the clean speech and all other; parameters.Without knowing the noise variance, NBSPcould be performed; directly on the noisy speech to infer the sparsity of the speech.; Experiments were executed on NOIZEUS database. Experiments are executed; on noisy speeches from NOIZEUS database with SNR ranging from 0 dB to 10; dB,which contain three types of noise (white,train and street).And the; subjective and objective measures like PESQ score and the output SegSNR; are implemented to evaluate the performance of NBSP and the other; state-of-the-art methods.Corresponding results show that NBSP achieves; better performances, especially in conditions of non-stationary noise; with low input SNR.