Journal ArticleDOI
A Data-Driven Approach to A Priori SNR Estimation
Suhadi Suhadi,Tim Fingscheidt +1 more
TLDR
A data-driven approach to a priori SNR estimation is presented, which reduces speech distortion, particularly in speech onset, while retaining a high level of noise attenuation in speech absence.Abstract:
The a priori signal-to-noise ratio (SNR) plays an important role in many speech enhancement algorithms. In this paper, we present a data-driven approach to a priori SNR estimation. It may be used with a wide range of speech enhancement techniques, such as, e.g., the minimum mean square error (MMSE) (log) spectral amplitude estimator, the super Gaussian joint maximum a posteriori (JMAP) estimator, or the Wiener filter. The proposed SNR estimator employs two trained artificial neural networks, one for speech presence, one for speech absence. The classical decision-directed a priori SNR estimator by Ephraim and Malah is broken down into its two additive components, which now represent the two input signals to the neural networks. Both output nodes are combined to represent the new a priori SNR estimate. As an alternative to the neural networks, also simple lookup tables are investigated. Employment of these data-driven nonlinear a priori SNR estimators reduces speech distortion, particularly in speech onset, while retaining a high level of noise attenuation in speech absence.read more
Citations
More filters
Journal ArticleDOI
Experimental Study on Extreme Learning Machine Applications for Speech Enhancement
TL;DR: The experimental results indicate that when the amount of training data is limited, both ELM- and H-ELM-based speech enhancement techniques consistently outperform the conventional BP-based shallow and deep learning algorithms, in terms of standardized objective evaluations, under various testing conditions.
Proceedings ArticleDOI
An investigation of spectral restoration algorithms for deep neural networks based noise robust speech recognition.
Bo Li,Yu Tsao,Khe Chai Sim +2 more
TL;DR: The preliminary experimental results on the Aurora 2 speech database show that with multi-condition training data the DNN itself is capable of learning robust representations, however, if only clean data is available, the MLSA algorithm is the best spectral restoration training method for DNNs.
Journal ArticleDOI
Generalized maximum a posteriori spectral amplitude estimation for speech enhancement
Yu Tsao,Ying-Hui Lai +1 more
TL;DR: The proposed generalized maximum a posteriori spectral amplitude (GMAPA) algorithm dynamically specifies the weight of prior density of speech spectra according to the SNR of the testing speech signals to calculate the optimal gain function.
Journal ArticleDOI
Optimization and evaluation of sigmoid function with a priori SNR estimate for real-time speech enhancement
TL;DR: Simulation results show that the proposed gain function, which can flexibly model exponential distributions, is a potential alternative speech enhancement gain function.
Journal ArticleDOI
Instantaneous A Priori SNR Estimation by Cepstral Excitation Manipulation
TL;DR: A novel a priori SNR estimator based on synthesizing an idealized excitation signal in the cepstral domain is introduced, which is less prone to sudden acoustic environmental changes and musical noise and able to preserve weak harmonic structures resulting in a spectrum that is more full-bodied.
References
More filters
Book
Adaptive Filter Theory
TL;DR: In this paper, the authors propose a recursive least square adaptive filter (RLF) based on the Kalman filter, which is used as the unifying base for RLS Filters.
Proceedings ArticleDOI
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
Martin Riedmiller,Heinrich Braun +1 more
TL;DR: A learning algorithm for multilayer feedforward networks, RPROP (resilient propagation), is proposed that performs a local adaptation of the weight-updates according to the behavior of the error function to overcome the inherent disadvantages of pure gradient-descent.
Journal ArticleDOI
Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator
Yariv Ephraim,David Malah +1 more
TL;DR: In this article, a system which utilizes a minimum mean square error (MMSE) estimator is proposed and then compared with other widely used systems which are based on Wiener filtering and the "spectral subtraction" algorithm.
Journal Article
Speech enhancement using a minimum mean square error short-time spectral amplitude estimator
TL;DR: This paper derives a minimum mean-square error STSA estimator, based on modeling speech and noise spectral components as statistically independent Gaussian random variables, which results in a significant reduction of the noise, and provides enhanced speech with colorless residual noise.
Book
Speech Enhancement: Theory and Practice
TL;DR: Clear and concise, this book explores how human listeners compensate for acoustic noise in noisy environments and suggests steps that can be taken to realize the full potential of these algorithms under realistic conditions.