Speech enhancement based on a priori signal to noise estimation

By P. Scalart, J. V. Filho. 1996

How researchers see this paper

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

Citations in the corpus

SEANet: A Multi-modal Speech Enhancement Network (2020, neutral): “Traditional signal processing methods adopt spectral noise subtraction [1, 2], spectral masking [3, 4], statistical methods based on Wiener ﬁltering [5] and Bayesian estimators [6, 7].”
A Wavenet for Speech Denoising (2017, methodology): “The baseline algorithm uses a Wiener filtering method based on a priori SNR estimation [23], as implemented here3.”
SEGAN: Speech Enhancement Generative Adversarial Network (2017, methodology): “Regarding the λ weight of our L 1 regularization, after some experimentation, we set it to 100 for the whole training.”
Cocktail Party Processing via Structured Prediction (2012, background): “In signal processing, speech enhancement (e.g., [1] [2]) has been extensively studied, and assumptions regarding the statistical properties of noise are crucial to its success.”
TCNN: Temporal Convolutional Neural Network for Real-time Speech Enhancement in the Time Domain (2019, unknown): “Traditional speech enhancement approaches include spectral subtraction methods [1], Wiener filtering [2], statistical model-based methods [3] and nonnegative matrix factorization [4].”
Unbiased MMSE-Based Noise Power Estimation With Low Complexity and Low Tracking Delay (2012, background): “However, all these methods have in common that they are a function of both the spectral noise power and the spectral speech power.”
Speech enhancement based on minimum mean-square error estimation and supergaussian priors (2005, background): “Therefore, improvements have been demonstrated with estimators which take the presence or absence of speech into account [2], [3], [11], [19].”
Reasons why current speech-enhancement algorithms do not improve speech intelligibility and suggested solutions (2011, methodology): “…sentences were processed by three different speech enhancement algorithms that included the Wiener algorithm based on a priori SNR estimation [14] and two spectral-subtractive algorithms based on reduced delay convolution [15] Let denote the magnitude of the noisy spectrum at time frame and…”
Deep Residual-Dense Lattice Network for Speech Enhancement (2020, unknown): “5) Wiener (Scalart and J.V 1996) 3.”
A Fully Convolutional Neural Network for Speech Enhancement (2016, background): “Decades of works showed feasible solutions which estimated the noise model and used it to recover noise-deducted speech [1, 2, 3, 4, 5].”
Robust signal-to-noise ratio estimation based on waveform amplitude distribution analysis (2008, background): “Reliable SNR estimation can improve algorithms for speech enhancement [1][2], speech detection, and speech recognition [3], since knowledge of SNR makes it easier to compensate for the effects of noise.”
SNR-Aware Convolutional Neural Network Modeling for Speech Enhancement (2016, background): “Successful examples include spectral subtraction [1], minimum-mean square error (MMSE) based spectral amplitude estimator [2], Wiener filtering [3], Karhunen-Loéve transformation (KLT) [4], and non-negative matrix factorization (NMF) [5].”
A Regression Approach to Speech Enhancement Based on Deep Neural Networks (2015, background): “I. INTRODUCTION I N RECENT years, single-channel speech enhancement has attracted a considerable amount of research attention because of the growing challenges in many important real-world applications, including mobile speech communication, hearing aids design and robust speech recognition [1].”
Equalization matching of speech recordings in real-world environments (2016, methodology): “Our best guess is to compute the filter G as the ratio: G(ω) = Ya(ω)/Yb(ω) (8)”
Separate Anything You Describe (2023, unknown): “To make a fair comparison with previous speech enhancement systems [6], [7], [69], [70], we resample all audio clips to 16 kHz.”
Subjective Comparison of Speech Enhancement Algorithms (2006, methodology): “The decision-directed approach was used for estimating the a priori SNR in the statistical methods and the Wiener as method [4] with a=0.98.”