1) Underdetermined speech separation
欠定混叠语音盲分离
2) Underdetermined blind separation
欠定盲分离
1.
The two-step approach is often used to separate sources in underdetermined blind separation problem.
针对目前欠定盲分离问题中源数未知,采取"两步法"进行分离源信号。
3) Separation of Overlapping Speech
混叠语音分离
1.
Separation of Overlapping Speech Based on Computational Auditory Scene Analysis;
基于计算声场景分析的混叠语音分离研究
5) Underdetermined Blind Source Separation
欠定盲源分离
1.
Under the sparse assumption,the problem of underdetermined blind source separation can be solved by l1-norm minimization algorithms such as the linear programming,the shortest-path algorithm,the combinatorial algo-rithm and so on.
基于稀疏假设,欠定盲源分离问题一般可采用线性规划、最短路径法和组合算法等l1范数最小化方法进行求解,但是这些传统方法对源信号的稀疏性要求较高,从而限制了源信号的估计精度。
6) blind speech separation
盲语音分离
1.
This paper describes a robust real-time blind speech separation method based on microphone array using delay-and-sum beamformer filter.
通过使用多波束形成器对盲分离系统进行预处理滤波,结合频域内独立分量分析的方法,提出了一种基于麦克阵列的快速实时盲语音分离系统,它能够有效地分离在真实环境中的卷积混叠语音信号。
补充资料：盲盲
1.谓茫茫无所见。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条