Independent Deeply Learned Matrix Analysis for Multichannel Audio Source Separation

2018/06/27 by Mogami, Shinichi, Sumino, Hayato, Kitamura, Daichi +4
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1806.10307

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.

Related

• Multichannel Audio Source Separation with Independent Deeply Learned Matrix Analysis Using Product of Source Models
• Empirical Bayesian Independent Deeply Learned Matrix Analysis For Multichannel Audio Source Separation
• Independent Deeply Learned Tensor Analysis for Determined Audio Source Separation
• Independent Low-Rank Matrix Analysis Based on Complex Student's t-Distribution for Blind Audio Source Separation
• Unsupervised Music Source Separation Using Differentiable Parametric Source Models