Blind Speech Separation Exploiting Temporal and Spectral Correlations Using Turbo Decoding of 2D-HMMs
european signal processing conference(2013)
摘要
We present a novel method to exploit correlations of adjacent time-frequency (TF)-slots for a sparseness-based blind speech separation (BSS) system. Usually, these correlations are exploited by some heuristic smoothing techniques in the post-processing of the estimated soft TF masks. We propose a different approach: Based on our previous work with one-dimensional (1D)-hidden Markov models (HMMs) along the time axis we extend the modeling to two-dimensional (2D)-HMMs to exploit both temporal and spectral correlations in the speech signal. Based on the principles of turbo decoding we solved the complex inference of 2D-HMMs by a modified forward-backward algorithm which operates alternatingly along the time and the frequency axis. Extrinsic information is exchanged between these steps such that increasingly better soft time-frequency masks are obtained, leading to improved speech separation performance in highly reverberant recording conditions.
更多查看译文
关键词
turbo decoding,spectral correlations,separation,d-hmms
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要