Speech enhancement for non-stationary noise environments

By Israel Cohen, Baruch Berdugo. Signal Processing, 2001

545 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4ffabfe2495e2030bb64468c18055bcefcf35222

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computational Mechanics

In Signal Processing

Citations in the corpus

Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks (2016, methodology): “As a conventional speech enhancement method we choose the method described in [30] that uses the optimally-modiﬁed log-spectral amplitude speech estimator (OMLSA) and an improved version of the minima controlled recursive averaging noise estimator as proposed in [31].”
Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement (2017, background): “Classical speech enhancement (SE) approaches, such as spectral subtraction [1], MMSE-based spectral amplitude estimator [2, 3] and optimally modiﬁed log-MMSE estimator [4, 5], are considered as unsupervised techniques having been studied extensively for several decades.”
Unbiased MMSE-Based Noise Power Estimation With Low Complexity and Low Tracking Delay (2012, background): “However , strictly speaking, this contradicts the definition of the a priori SPP. Substituting (16) and (17) into (15) we obtain for the a posteriori SPP (e.g., [27] ) (18) where in this work, we assume .”
Fullsubnet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement (2020, background): “The temporal evolution of frequency-wise STFT magnitude reﬂects the stationarity, which is the foundation for the conventional noise power estimators [12, 13] and speech enhancement methods [14, 15].”
A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, unknown): “In [265], a soft mask is proposed based on a mapping between the ITD values and the relative contribution of the target source.”
A Regression Approach to Speech Enhancement Based on Deep Neural Networks (2015, methodology): “An improved version of OM-LSA [8], [9], denoted as LogMMSE, was used for performance comparison with our DNN approach.”
Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech (2016, unknown): “As a conventional speech enhancement method we choose the statistical model-based method described in [31] that uses the optimally-modiﬁed log-spectral amplitude speech estimator (OMLSA) and an improved version of the minima controlled recursive averaging noise estimator as proposed in [32].”
An Experimental Study on Speech Enhancement Based on Deep Neural Networks (2014, methodology): “The optimal spectral gain function of them, which minimizes the mean-square error of the log-spectra, is obtained as a weighted geometric mean of the hypothetical gains associated with the speech presence uncertainty [15].”
Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging (2003, methodology): “Recently, we introduced a noise estimation approach, namely Minima Controlled Recursive Averaging (MCRA) [3], [4], that combines the robustness of the minimum tracking with the simplicity of the recursive averaging.”
Noise estimation by minima controlled recursive averaging for robust speech enhancement (2002, methodology): “[6]. Moreover, this method may occasionally attenuate low energy phonemes, particularly if the minimum search window is too short [ 7 ].”