Speech Enhancement by Short-Time Spectrum Estimation with Multivariate Laplace Speech Model
نویسندگان
چکیده
The paper presents a new short-time spectrum estimation algorithm for speech enhancement. A novel multivariate Laplace speech model is utilized to characterize the dependencies between adjacent DFT coefficients of speech, based on which a minimum mean-square error (MMSE) estimator of speech spectral components is derived. Moreover, the speech presence uncertainty is incorporated to modify the MMSE estimator. Experimental results show that the developed algorithm achieves better noise suppression and lower speech distortion compared to the existing speech enhancement methods. Streszczenie. W artykule przedstawiono nowy algorytm estymacji krótkookresowego spektrum głosu do poprawy dźwięku mowy. Wykorzystano wieloczynnikowy model Laplace’a w celu scharakteryzowania zależności pomiędzy składnikami DFT dźwięku mowy. Na tej podstawie obliczane jest minimum błędu średnio-kwadratowego dla estymatora. Wyniki eksperymentalne potwierdzają ulepszoną skuteczność eliminacji zakłóceń mowy, w porównaniu ze stosowanymi metodami. (Wieloczynnikowy model mowy Laplace’a w estymatorze spektrum krótkookresowego, na potrzeby polepszenia dźwięku)
منابع مشابه
Speech enhancement based on hidden Markov model using sparse code shrinkage
This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...
متن کاملSingle Channel Speech Enhancement Using MMSE Estimation of Short-Time Modulation Magnitude Spectrum
In this paper we investigate the enhancement of speech by applying MMSE short-time spectral magnitude estimation in the modulation domain. For this purpose, the traditional analysismodification-synthesis framework is extended to include modulation domain processing. We compensate the noisy modulation spectrum for additive noise distortion by applying the MMSE short-time spectral magnitude estim...
متن کاملSpeech Enhancement Using Gaussian Mixture Models, Explicit Bayesian Estimation and Wiener Filtering
Gaussian Mixture Models (GMMs) of power spectral densities of speech and noise are used with explicit Bayesian estimations in Wiener filtering of noisy speech. No assumption is made on the nature or stationarity of the noise. No voice activity detection (VAD) or any other means is employed to estimate the input SNR. The GMM mean vectors are used to form sets of over-determined system of equatio...
متن کاملComputationally efficient speech enhancement by spectral minima tracking in subbands
| We present an eecient algorithm for the enhancement of speech signals which are heavily corrupted by short-time stationary, acoustically or electrically added disturbances. The algorithm is based on spectral amplitude estimation using an overlap-add FFT lter bank system. Compared to other systems , the improved performance of our speech enhancement system is achieved by the combination of the...
متن کاملSpeech enhancement using a minimum mean-square error short-time spectral modulation magnitude estimator
In this paper we investigate the enhancement of speech by applying MMSE short-time spectral magnitude estimation in the modulation domain. For this purpose, the traditional analysis-modification-synthesis framework is extended to include modulation domain processing. We compensate the noisy modulation spectrum for additive noise distortion by applying the MMSE short-time spectral magnitude esti...
متن کامل