Loading...
Search for:
vad
0.005 seconds
Speech Enhancement Based on Statistical Methods
,
Ph.D. Dissertation
Sharif University of Technology
;
Sameti, Hossein
(Supervisor)
Abstract
Signle-channel speech enhancement using hidden Markov model (HMM) based on minimum mean square error (MMSE) estimator is focused on and an HMM-based speech enhancement in Mel-frequency domain is proposed. The MMSE estimator results in a weighted sum filtering of the noisy signal in which accurate estimation of the filter values and filter weights comprise the main challenges. The cepstral domain modeling for speech enhancement is motivated by accurate filter selection in this domain. In the propsed framework, Mel-frequency spectral (MFS) and Mel-frequency cepstral (MFC) features are studied and experimented. In addition to the spectrum estimator, magnitude spectrum, log-magnitude spectrum...
A comparative study on single-channel noise estimation methods for speech enhancement
, Article International Conference on Intelligent Systems Design and Applications, ISDA ; 2012 , Pages 645-650 ; 21647143 (ISSN) ; 9781467351188 (ISBN) ; Sameti, H ; Sharif University of Technology
2012
Abstract
This paper studies a number of well-known noise estimation techniques and provides a comparative performance analysis of them in speech enhancement platform. Two types of evaluation data that simulate consistent and inconsistent noisy conditions are prepared in the presence of six noise types at different SNR levels. The performance of speech enhancement systems and the spectrum distance of the estimated and original noise spectrums are used as evaluation criteria. The evaluations indicate that a simple VAD method outperforms noise estimation methods in most of the consistent noisy conditions
Probabilistic CFD analysis on the flow field and performance of the FDA centrifugal blood pump
, Article Applied Mathematical Modelling ; Volume 109 , 2022 , Pages 555-577 ; 0307904X (ISSN) ; Karimi, M. S ; Raisee, M ; Sharbatdar, M ; Sharif University of Technology
Elsevier Inc
2022
Abstract
The present study is set out to systematically investigate the combined impact of operational, geometrical, and model uncertainties on the hemodynamics and performance characteristics in the U.S. Food and Drug Administration (FDA) benchmark centrifugal blood pump. Non-intrusive Polynomial Chaos Expansion (NIPCE) has been utilized to propagate the uncertainty of 12 random input variables in the flow field and the performance characteristics of the blood pump at three working conditions. The global sensitivity of the Quantities of Interest (QoI) to the uncertain input parameters was measured through the Sobol’ indices. The Multiple Reference Frames (MRF) approach and the SST k−ω turbulence...