Enhancement of Noisy Speech Signal by Non-Local Means Estimation of Variational Mode Functions

Nagapuri Srinivas, Gayadhar Pradhan, Syed Shahnawazuddin


In this paper, a speech enhancement approach exploiting the efficacy of non-local means (NLM) estimation and variational mode decomposition (VMD) is proposed. The NLMestimation is effective in removing noises whenever non-local similarities are present among the samples of the signal under consideration. However, it suffers from the issue of under-averaging in those regions where amplitude and frequency variations are abrupt. Since speech is a non-stationary signal, the magnitude and frequency vary over the time. Consequently, NLM is not that effective in removing the noise components from the speech signal as observed in the case of image enhancement. To address this issue, the noisy speech signal is first decomposed into variational mode functions (VMFs) using VMD. Each of the VMFs represents a small portion of the overall frequency components of the signal. The VMFs are then combined into different groups depending on their similarities to reduce computational cost. Next, the non-local similarity present in each group of VMFs is exploited for an effective speech enhancement through NLM estimation. The enhancement performance of the proposed method is compared with two existing speech enhancement techniques. The experimental results presented in this study show that, the proposed method provides better speech enhancement performance.


 DOI: 10.21437/Interspeech.2018-1928

Cite as: Srinivas, N., Pradhan, G., Shahnawazuddin, S. (2018) Enhancement of Noisy Speech Signal by Non-Local Means Estimation of Variational Mode Functions. Proc. Interspeech 2018, 1156-1160, DOI: 10.21437/Interspeech.2018-1928.


@inproceedings{Srinivas2018,
  author={Nagapuri Srinivas and Gayadhar Pradhan and Syed Shahnawazuddin},
  title={Enhancement of Noisy Speech Signal by Non-Local Means Estimation of Variational Mode Functions},
  year=2018,
  booktitle={Proc. Interspeech 2018},
  pages={1156--1160},
  doi={10.21437/Interspeech.2018-1928},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1928}
}