Z Wang, F Sha - … Conference on Acoustics, Speech and Signal …, 2014 - ieeexplore.ieee.org
Non-negative matrix factorization (NMF) has emerged as a promising approach for single- channel speech separation. In this paper, we propose a new method of discriminative …
N Guan, L Lan, D Tao, Z Luo… - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
Regarding the non-negativity property of the magnitude spectrogram of speech signals, nonnegative matrix factorization (NMF) has obtained promising performance for speech …
F Weninger, A Lehmann… - 2011 IEEE International …, 2011 - ieeexplore.ieee.org
We describe and evaluate our toolkit openBliSSART (open-source Blind Source Separation for Audio Recognition Tasks), which is the C++ framework and toolbox that we have …
B King, L Atlas - … Conference on Acoustics, Speech and Signal …, 2010 - ieeexplore.ieee.org
Although the task seems trivial for human listeners, research in automating source separation still lags far behind human performance and is especially difficult for single …
DL Sun, GJ Mysore - 2013 IEEE International Conference on …, 2013 - ieeexplore.ieee.org
Supervised and semi-supervised source separation algorithms based on non-negative matrix factorization have been shown to be quite effective. However, they require isolated …
We are surrounded by sounds. Such a noisy environment makes it difficult to hear desired speech and to converse comfortably. This makes it important to be able to separate and …
J Le Roux, JR Hershey… - 2015 IEEE International …, 2015 - ieeexplore.ieee.org
Non-negative matrix factorization (NMF) has been widely used for challenging single- channel audio source separation tasks. However, inference in NMF-based models relies on …
T Virtanen, AT Cemgil - … Component Analysis and Signal Separation: 8th …, 2009 - Springer
This paper deals with audio source separation using supervised non-negative matrix factorization (NMF). We propose a prior model based on mixtures of Gamma distributions for …
This paper presents supervised feature learning approaches for speaker identification that rely on nonnegative matrix factorisation. Recent studies have shown that group nonnegative …