A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize...
详细信息
A machine learning based speech enhancement method is proposed to improve the intelligibility of whispered speech. A binary mask estimated by a two-class support vector machine （SVM） classifier is used to synthesize the enhanced whisper. A novel noise robust feature called Gammatone feature cosine coefficients （GFCCs） extracted by an auditory periphery model is derived and used for the binary mask estimation. The intelligibility performance of the proposed method is evaluated and compared with the traditional speech enhancement methods. Objective and subjective evaluation results indicate that the proposed method can effectively improve the intelligibility of whispered speech which is contaminated by noise. Compared with the power subtract algorithm and the log-MMSE algorithm, both of which do not improve the intelligibility in lower signal-to-noise ratio （SNR） environments, the proposed method has good performance in improving the intelligibility of noisy whisper. Additionally, the intelligibility of the enhanced whispered speech using the proposed method also outperforms that of the corresponding unprocessed noisy whispered speech.
传统多目标优化算法(Multi-objective evolution algorithms,MOEAs)的基本框架大致分为两部分:首先是收敛性保持,采用Pareto支配方法将种群分成若干非支配层;其次是分布性保持,在临界层中,采用分布性保持机制维持种群的分布性.然而在处理高维优化问题(Many-objective optimization problems,MOPs)(目标维数大于3)时,随着目标维数的增加,种群的收敛性和分布性的冲突加剧,Pareto支配关系比较个体优劣的能力也迅速下降,此时传统的MOEA已不再适用于高维优化问题.鉴于此,本文提出了一种基于邻域竞赛的多目标优化算法(Evolutionary algorithm based on neighborhood competition for multi-objective optimization,NCEA).NCEA首先将个体的各个目标之和作为个体的收敛性估计;然后,计算当前个体向量与收敛性最好的个体向量之间的夹角,并将其作为当前个体的邻域估计;最后,通过邻域竞赛方法将问题划分为若干个相互关联的子问题并逐步优化.为了验证NCEA的有效性,本文选取5个优秀的算法与NCEA进行对比实验.通过对比实验验证,NCEA具有较强的竞争力,能同时保持良好的收敛性和分布性.
暂无评论