INVESTIGATION ON THE INFLUENCE OF PARAMETERIZATIONIN SPEECH ENHANCEMENT USING LOW RANK SPARSE DECOMPOSITION MODELS UNDER LOW SNR CONDITIONS.

Volume 20 No 6 (2022)

Sridhar K V, Kishore Kumar T

DOI: 10.14704/nq.2022.20.6.NQ22926

Abstract

In this work, the influence of the various parameters of an unsupervised speech enhancement (SE) based on the recent development of low-rank and sparse matrix decomposition models investigated. The proposed framework decomposes the noisy speech spectrogram into three submatrices: the noise structure matrix, the clean speech structure matrix, and the residual noise matrix

Keywords

Speech enhancement, Low rank sparse models, Low SNR, Speech to distortion ratio, Mask

Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.