Stereophonic spectrogram segmentation using Markov random fields
MLSP(2012)
摘要
There is a good amount of similarity between source separation approaches that use spectrograms captured from multiple microphones and computer vision algorithms that use multiple images for segmentation problems. Just as one would use Markov random fields (MRF) to solve image segmentation problems, we propose a method of modeling source separation using MRFs, and then solving such problems via common MRF inference methods. To this end, as a preprocessing, we convert stereophonic spectrograms into a integrated form based on their inter-channel level differences (ILD), which is a procedure analogous to getting a disparity map from stereo images for matching problems. Given the ILD matrix as an observed image, we estimate latent labels which stand for the responsibility of each spectrogram's time/frequency bin to a specific sound source. It is shown that the proposed method shows reasonable separation performance in a variety of mixing environments including online separation and moving sources. We expect this new way of formulating source separation problems to help exploit advantages of probabilistic graphical models and the recent advances in low-power, high-performance hardware suited for such tasks.
更多查看译文
关键词
interchannel level differences,spectrogram time-frequency bin,source separation modeling,observed image,acoustic generators,image matching,multiple images segmentation problems,blind source separation,stereo images,computer vision algorithms,probabilistic graphical models,inference mechanisms,probabilistic graphical model,image segmentation,multiple microphones,matrix algebra,moving sources,stereophonic spectrogram segmentation,ild matrix,reasonable separation performance,source separation,common mrf inference methods,image sampling,low-power high-performance hardware,disparity map,computer vision,image matching problems,mixing environments,stereo image processing,markov random fields,markov processes,mrf,gibbs sampling,time-frequency analysis,time frequency analysis,time frequency,graphical model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络