Multichannel audio signal source separation based on an Interchannel Loudness Vector Sum

TL;DR

This paper introduces a novel blind source separation algorithm for multichannel audio, leveraging inter-channel loudness differences and EM clustering to effectively separate background and object sources in 5.1 and 7.1 audio formats.

Contribution

The paper presents a new BSS method specifically designed for multichannel audio using ILVS and EM clustering, addressing limitations of stereo-focused algorithms.

Findings

Successfully separates common and object sound sources

Effective on 5.1 and 7.1 channel audio

Potential applications in upmix and cinema audio systems

Abstract

In this paper, a Blind Source Separation (BSS) algorithm for multichannel audio contents is proposed. Unlike common BSS algorithms targeting stereo audio contents or microphone array signals, our technique is targeted at multichannel audio such as 5.1 and 7.1ch audio. Since most multichannel audio object sources are panned using the Inter-channel Loudness Difference (ILD), we employ the ILVS (Inter-channel Loudness Vector Sum) concept to cluster common signals (such as background music) from each channel. After separating the common signals from each channel, we employ an Expectation Maximization (EM) algorithm with a von-Mises distribution to successfully classify the clustering of sound source objects and separate the audio signals from the original mixture. Our proposed method can therefore separate common audio signals and object source signals from multiple channels with reasonable quality. Our multichannel audio content separation technique can be applied to an upmix system or a cinema audio system requiring multichannel audio source separation.