In this paper,two speech enhancement systems with supergaussian speech modeling are presented. The clean speech components are estimated by Minimum-Mean-Square-Error (MMSE) es-timator under the assumption that the DCT...In this paper,two speech enhancement systems with supergaussian speech modeling are presented. The clean speech components are estimated by Minimum-Mean-Square-Error (MMSE) es-timator under the assumption that the DCT coefficients of clean speech are modeled by a Laplacian or a Gamma distribution and the DCT coefficients of the noise are Gaussian distributed. Then,MMSE estimators under speech presence uncertainty are derived. Furthermore,the proper estimators of the speech statistical parameters are proposed. The speech Laplacian factor is estimated by a new deci-sion-directed method. The simulation results show that the proposed algorithm yields less residual noise and better speech quality than the Gaussian based speech enhancement algorithms proposed in recent years.展开更多
An improved speech absence probability estimation was proposed using environmental noise classification for speech enhancement.A relevant noise estimation approach,known as the speech presence uncertainty tracking met...An improved speech absence probability estimation was proposed using environmental noise classification for speech enhancement.A relevant noise estimation approach,known as the speech presence uncertainty tracking method,requires seeking the "a priori" probability of speech absence that is derived by applying microphone input signal and the noise signal based on the estimated value of the "a posteriori" signal-to-noise ratio(SNR).To overcome this problem,first,the optimal values in terms of the perceived speech quality of a variety of noise types are derived.Second,the estimated optimal values are assigned according to the determined noise type which is classified by a real-time noise classification algorithm based on the Gaussian mixture model(GMM).The proposed algorithm estimates the speech absence probability using a noise classification algorithm which is based on GMM to apply the optimal parameter of each noise type,unlike the conventional approach which uses a fixed threshold and smoothing parameter.The performance of the proposed method was evaluated by objective tests,such as the perceptual evaluation of speech quality(PESQ) and composite measure.Performance was then evaluated by a subjective test,namely,mean opinion scores(MOS) under various noise environments.The proposed method show better results than existing methods.展开更多
Consider the following heteroscedastic semiparametric regression model：where {Xi, 1 〈 i 〈 n} are random design points, errors {ei, 1 〈 i 〈 n} are negatively associated （NA） random variables, （r2 = h（ui）, and...Consider the following heteroscedastic semiparametric regression model：where {Xi, 1 〈 i 〈 n} are random design points, errors {ei, 1 〈 i 〈 n} are negatively associated （NA） random variables, （r2 = h（ui）, and {ui} and {ti} are two nonrandom sequences on [0, 1]. Some wavelet estimators of the parametric component β, the non- parametric component g（t） and the variance function h（u） are given. Under some general conditions, the strong convergence rate of these wavelet estimators is O（n- 1 log n）. Hence our results are extensions of those re, sults on independent random error settings.展开更多
This paper considers experimental situations where the interested effects have to be or- thogonal to a set of nonnegligible effects. It is shown that various types of orthogonal arrays with mixed strength are A-optima...This paper considers experimental situations where the interested effects have to be or- thogonal to a set of nonnegligible effects. It is shown that various types of orthogonal arrays with mixed strength are A-optimal for estimating the parameters in ANOVA high dimension model representation. Both cases including interactions or not are considered in the model. In particularly, the estimations of all main effects are A-optimal in a mixed strength （2, 2）3 orthogonal array and the estimations of all main effects and two-factor interactions in G~ x G~ are A-optimal in a mixed strength （2, 2）4 orthogonal array. The properties are also illustrated through a simulation study.展开更多
The strong consistency of M estimators of the regression parameters in linear models for ρ-mixing random errors under some mild conditions is established, which is an essential improvement over the relevant results i...The strong consistency of M estimators of the regression parameters in linear models for ρ-mixing random errors under some mild conditions is established, which is an essential improvement over the relevant results in the literature on the moment conditions and mixing errors. Especially, Theorem of Wu （2005） is improved essentially on the moment conditions.展开更多
基金the Natural Science Foundation of Jiangsu Province (No.BK2006001).
文摘In this paper,two speech enhancement systems with supergaussian speech modeling are presented. The clean speech components are estimated by Minimum-Mean-Square-Error (MMSE) es-timator under the assumption that the DCT coefficients of clean speech are modeled by a Laplacian or a Gamma distribution and the DCT coefficients of the noise are Gaussian distributed. Then,MMSE estimators under speech presence uncertainty are derived. Furthermore,the proper estimators of the speech statistical parameters are proposed. The speech Laplacian factor is estimated by a new deci-sion-directed method. The simulation results show that the proposed algorithm yields less residual noise and better speech quality than the Gaussian based speech enhancement algorithms proposed in recent years.
基金Project supported by an Inha University Research GrantProject(10031764) supported by the Strategic Technology Development Program of Ministry of Knowledge Economy,Korea
文摘An improved speech absence probability estimation was proposed using environmental noise classification for speech enhancement.A relevant noise estimation approach,known as the speech presence uncertainty tracking method,requires seeking the "a priori" probability of speech absence that is derived by applying microphone input signal and the noise signal based on the estimated value of the "a posteriori" signal-to-noise ratio(SNR).To overcome this problem,first,the optimal values in terms of the perceived speech quality of a variety of noise types are derived.Second,the estimated optimal values are assigned according to the determined noise type which is classified by a real-time noise classification algorithm based on the Gaussian mixture model(GMM).The proposed algorithm estimates the speech absence probability using a noise classification algorithm which is based on GMM to apply the optimal parameter of each noise type,unlike the conventional approach which uses a fixed threshold and smoothing parameter.The performance of the proposed method was evaluated by objective tests,such as the perceptual evaluation of speech quality(PESQ) and composite measure.Performance was then evaluated by a subjective test,namely,mean opinion scores(MOS) under various noise environments.The proposed method show better results than existing methods.
基金supported by the National Natural Science Foundation of China (No. 11071022)the Key Project of the Ministry of Education of China (No. 209078)the Youth Project of Hubei Provincial Department of Education of China (No. Q20122202)
文摘Consider the following heteroscedastic semiparametric regression model：where {Xi, 1 〈 i 〈 n} are random design points, errors {ei, 1 〈 i 〈 n} are negatively associated （NA） random variables, （r2 = h（ui）, and {ui} and {ti} are two nonrandom sequences on [0, 1]. Some wavelet estimators of the parametric component β, the non- parametric component g（t） and the variance function h（u） are given. Under some general conditions, the strong convergence rate of these wavelet estimators is O（n- 1 log n）. Hence our results are extensions of those re, sults on independent random error settings.
基金the National Natural Science Foundation of China under Grant Nos.11171065,11301073the Natural Science Foundation of Jiangsu under Grant No.BK20141326+1 种基金the Research Fund for the Doctoral Program of Higher Education of China under Grant No.20120092110021Scientific Research Foundation of Graduate School of Southeast University under Grant No.YBJJ1444
文摘This paper considers experimental situations where the interested effects have to be or- thogonal to a set of nonnegligible effects. It is shown that various types of orthogonal arrays with mixed strength are A-optimal for estimating the parameters in ANOVA high dimension model representation. Both cases including interactions or not are considered in the model. In particularly, the estimations of all main effects are A-optimal in a mixed strength （2, 2）3 orthogonal array and the estimations of all main effects and two-factor interactions in G~ x G~ are A-optimal in a mixed strength （2, 2）4 orthogonal array. The properties are also illustrated through a simulation study.
基金This research is supported by the National Natural Science Foundation of China under Grant No. 11061012, the Support Program of the New Century Guangxi China Ten-hundred-thousand Talents Project under Grant No. 2005214, and the Guangxi, China Science Foundation under Grant No. 0991081.
文摘The strong consistency of M estimators of the regression parameters in linear models for ρ-mixing random errors under some mild conditions is established, which is an essential improvement over the relevant results in the literature on the moment conditions and mixing errors. Especially, Theorem of Wu （2005） is improved essentially on the moment conditions.
