Accelerating Non-Negative Matrix Factorization for Audio Source Separation on Multi-Core and Many-Core Architectures

Audio Source Separation with Discriminative Scattering Networks

In this report we describe an ongoing line of research for solving single-channel source separation problems. Many monaural signal decomposition techniques proposed in the literature operate on a feature space consisting of a time-frequency representation of the input data. A challenge faced by these approaches is to effectively exploit the temporal dependencies of the signals at scales larger ...

Intelligent Single-Channel Methods for Multi-Source Audio Analysis

This thesis investigates the potential of recent machine learning methods for the challenging task of single-channel, multi-source audio audio analysis, i.e., information extraction from single-channel audio where the sources of interest (e.g., speech) are mixed with multiple interfering sources. First, it is shown that source separation by recently proposed techniques for non-negative matrix f...

Robust speech recognition in multi-source noise environments using convolutive non-negative matrix factorization

Convolutive non-negative matrix factorization (CNMF) is an effective approach for supervised audio source separation. It relies on the availability of sufficient training data to learn a set of bases for each acoustic source. For automatic speech recognition (ASR) in a multi-source noise environment, the varied nature of background noise makes it a challenging task to learn the noise bases and ...

Non-Negative Matrix Factorization with Sparsity Learning for Single Channel Audio Source Separation

Comparing Separation Quality of Nonnegative Matrix Factorization and Nonnegative Matrix Factor 2D Deconvolution in Audio Source Separation Tasks

The Nonnegative Matrix Factorization (NMF) is widely used in audio source separation tasks. However, the separation quality of NMF varies a lot depending on the mixture. In this paper, we analyze the use of NMF in source separation tasks and show how separation results can be significantly improved by using the Nonnegative Matrix Factor 2D Deconvolution (NMF2D). NMF2D was originally proposed as...