基于机器学习的欠定语音分离方法研究-信息与通信工程专业论文.docxVIP

基于机器学习的欠定语音分离方法研究Machine 基于机器学习的欠定语音分离方法研究 Machine Learning for Underdetermined Speech Separation Abstract Speech separation technology plays important role in many speech processing systems such speech recognition and speaker recognition．Speech in high quality is not only to meet the demand of human hearing better，but also important guarantee for the subsequent speech processing．In the actual scenario，signals often interfered by noise，which makes speech separation has become hot topic over the years．The of speech separation is to separate the signals from the observed mixture。 This paper focus the underdetermined speech separation problem．The main research work can be included as following aspects： (1)A novel extraction method based stepwise separation and softmax classifier is proposed in this paper．The algorithm is suitable for extracting the interested signal from mixture．With any utterance from target speaker，called referenced signal，the target signal be identified by the soflmax classifier trained by the single source points from each source．Then the target signal is extracted by the stepwise separation method layer by layer．The proposed method could extract target signal well with low computational complexity and doesn’t require much priori information． (2)Based strong feature extraction capability and nonlinear mapping ability of deep neural network(DNY)，a supervised and strong discriminative single channel speech separation(SCSS)method is proposed．The correlation coefficients and negentropy added to the objective function in order to reduce the interference．Moreover，a new training strategy based curriculum learning to further enhance the separation performance is explored．The training samples sorted by ranking function firstly and then gradually introduced into DNN training from easy to complex．The experimental results show that the proposed algorithm outperforms the contrasting approaches． (3)This paper combines the matrix factorization(MF)and deep neural