English

Independent Deeply Learned Matrix Analysis for Multichannel Audio Source Separation

Audio and Speech Processing 2018-06-28 v1 Sound

Abstract

In this paper, we address a multichannel audio source separation task and propose a new efficient method called independent deeply learned matrix analysis (IDLMA). IDLMA estimates the demixing matrix in a blind manner and updates the time-frequency structures of each source using a pretrained deep neural network (DNN). Also, we introduce a complex Student's t-distribution as a generalized source generative model including both complex Gaussian and Cauchy distributions. Experiments are conducted using music signals with a training dataset, and the results show the validity of the proposed method in terms of separation accuracy and computational cost.

Keywords

Cite

@article{arxiv.1806.10307,
  title  = {Independent Deeply Learned Matrix Analysis for Multichannel Audio Source Separation},
  author = {Shinichi Mogami and Hayato Sumino and Daichi Kitamura and Norihiro Takamune and Shinnosuke Takamichi and Hiroshi Saruwatari and Nobutaka Ono},
  journal= {arXiv preprint arXiv:1806.10307},
  year   = {2018}
}

Comments

5 pages, 4 figures, To appear in the Proceedings of the 26th European Signal Processing Conference (EUSIPCO 2018)

R2 v1 2026-06-23T02:43:05.091Z