Joint Sound Source Separation And Speaker Recognition

Abstract

Non-negative Matrix Factorization (NMF) has already been applied to learn speaker characterizations from single or non-simultaneous speech for speaker recognition applications. It is also known for its good performance in (blind) source separation for simultaneous speech. This paper explains how NMF can be used to jointly solve the two problems in a multichannel speaker recognizer for simultaneous speech. It is shown how state-of-the-art multichannel NMF for blind source separation can be easily extended to incorporate speaker recognition. Experiments on the CHiME corpus show that this method outperforms the sequential approach of first applying source separation, followed by speaker recognition that uses state-of-the-art i-vector techniques.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyzegers2016joint

Related papers

• Complex NMF Under Phase Constraints Based On Signal Modeling: Application To Audio Source Separation (2016)7.50
• Determined Multichannel Blind Source Separation With Clustered Source Model (2024)0.00
• Multichannel Blind Speech Source Separation With A Disjoint Constraint Source Model (2024)0.00
• Accelerated Convolutive Transfer Function-based Multichannel NMF Using Iterative Source Steering (2025)0.00
• Supervised And Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization (2017)18.80
• Generalized Multichannel Variational Autoencoder For Underdetermined Source Separation (2018)7.81
• End-to-end Non-negative Autoencoders For Sound Source Separation (2019)2.26
• Multichannel Singing Voice Separation By Deep Neural Network Informed DOA Constrained CNMF (2020)5.84