Separation of Moving Sound Sources Using Multichannel NMF and Acoustic Tracking

    Research output: Contribution to journalArticleScientificpeer-review

    15 Citations (Scopus)

    Abstract

    In this paper we propose a method for separation of moving sound sources. The method is based on first tracking the sources and then estimation of source spectrograms using multichannel non-negative matrix factorization (NMF) and extracting the sources from the mixture by single-channel Wiener filtering. We propose a novel multichannel NMF model with time-varying mixing of the sources denoted by spatial covariance matrices (SCM) and provide update equations for optimizing model parameters minimizing squared Frobenius norm. The SCMs of the model are obtained based on estimated directions of arrival of tracked sources at each time frame. The evaluation is based on established objective separation criteria and using real recordings of two and three simultaneous moving sound sources. The compared methods include conventional beamforming and ideal ratio mask separation. The proposed method is shown to exceed the separation quality of other evaluated blind approaches according to all measured quantities. Additionally, we evaluate the method's susceptibility towards tracking errors by comparing the separation quality achieved using annotated ground truth source trajectories.

    Original languageEnglish
    Pages (from-to)281-295
    JournalIEEE/ACM Transactions on Audio Speech and Language Processing
    Volume26
    Issue number2
    Early online date16 Nov 2017
    DOIs
    Publication statusPublished - 2018
    Publication typeA1 Journal article-refereed

    Keywords

    • acoustic source tracking
    • Acoustics
    • Array signal processing
    • Direction-of-arrival estimation
    • Estimation
    • Mathematical model
    • microphone arrays
    • Microphones
    • moving sound sources
    • Sound source separation
    • Spectrogram
    • time-varying mixing model

    Publication forum classification

    • Publication forum level 2

    ASJC Scopus subject areas

    • Signal Processing
    • Media Technology
    • Instrumentation
    • Acoustics and Ultrasonics
    • Linguistics and Language
    • Electrical and Electronic Engineering
    • Speech and Hearing

    Fingerprint

    Dive into the research topics of 'Separation of Moving Sound Sources Using Multichannel NMF and Acoustic Tracking'. Together they form a unique fingerprint.

    Cite this