A Pairwise Algorithm Using the Deep Stacking Network for Speech Separation and Pitch Estimation
A Pairwise Algorithm Using the Deep Stacking Network for Speech Separation and Pitch Estimation
复制标题
DOI：
10.1109/taslp.2016.2540805
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
Xueliang Zhang;Hui Zhang;Shuai Nie;Guanglai Gao;Wenju Liu
中科院分区：
文献类型：
--
作者：
Xueliang Zhang;Hui Zhang;Shuai Nie;Guanglai Gao;Wenju Liu
噪声环境下的语音分离和基音估计被认为是一个“先有鸡还是先有蛋”的问题。一方面，基音信息是语音分离的重要线索。另一方面，语音分离使得当去除背景噪声时更容易进行基音估计。在本文中，我们提出了一个监督学习架构来迭代地解决这两个问题。该算法基于深度堆叠网络（DSN），提供了一种堆叠简单处理模块以构建深度架构的方法。每个模块都是一个分类器，其目标是理想二进制掩码（IBM），输入向量包括频谱特征，基于音高的特征和前一个模块的输出。在测试阶段，我们使用分离结果估计音高，并将基于音高的特征更新到下一个模块。当嵌入到DSN中时，音高估计和语音分离每个都运行几次。我们从最后一个模块获得最终结果。系统的评估表明，该系统的结果在高质量的估计二进制掩码和准确的基音估计，并优于最近的系统在其泛化能力。
Speech separation and pitch estimation in noisy conditions are considered to be a “chicken-and-egg” problem. On one hand, pitch information is an important cue for speech separation. On the other hand, speech separation makes pitch estimation easier when background noise is removed. In this paper, we propose a supervised learning architecture to solve these two problems iteratively. The proposed algorithm is based on the deep stacking network (DSN), which provides a method for stacking simple processing modules to build deep architectures. Each module is a classifier whose target is the ideal binary mask (IBM), and the input vector includes spectral features, pitch-based features and the output from the previous module. During the testing stage, we estimate the pitch using the separation results and update the pitch-based features to the next module. When embedded into the DSN, pitch estimation and speech separation each run several times. We obtain the final results from the last module. Systematic evaluations show that the proposed system results in both a high quality estimated binary mask and accurate pitch estimation and outperforms recent systems in its generalization ability.