Wyniki wyszukiwania - BazTech

1

Deep Neural Network for Supervised Single-Channel Speech Enhancement

Saleem Nasir, Irfan Khattak Muhammad, Ali Muhammad Yousaf, Shafi Muhammad

Archives of Acoustics

|

2019

|

Vol. 44, No. 1

3--12

EN

Speech enhancement is fundamental for various real time speech applications and it is a challenging task in the case of a single channel because practically only one data channel is available. We have proposed a supervised single channel speech enhancement algorithm in this paper based on a deep neural network (DNN) and less aggressive Wiener filtering as additional DNN layer. During the training stage the network learns and predicts the magnitude spectrums of the clean and noise signals from input noisy speech acoustic features. Relative spectral transform-perceptual linear prediction (RASTA-PLP) is used in the proposed method to extract the acoustic features at the frame level. Autoregressive moving average (ARMA) filter is applied to smooth the temporal curves of extracted features. The trained network predicts the coefficients to construct a ratio mask based on mean square error (MSE) objective cost function. The less aggressive Wiener filter is placed as an additional layer on the top of a DNN to produce an enhanced magnitude spectrum. Finally, the noisy speech phase is used to reconstruct the enhanced speech. The experimental results demonstrate that the proposed DNN framework with less aggressive Wiener filtering outperforms the competing speech enhancement methods in terms of the speech quality and intelligibility.

2

Impact of dielectric deterioration on the conducted EMI emissions in the DC-DC boost converter

Musznicki P., Schanen J. L., Granjon P., Juszcz J.

Przegląd Elektrotechniczny

|

2011

|

R. 87, nr 2

179-183

EN

The magnitude of emitted noise generated by DC-DC converters depends of their electrical behavior and parameters. Some of these can change during the converter life time, especially due to some deterioration process. In this paper the impact of the dielectric materials aging is presented using both circuit simulation and a digital signal processing method based on Wiener filtering. The change of the total EMI spectrum as a function of the dielectric property has been investigated. Application can be either aging diagnostig, or a forecast of the EMI spectrum evolution with the time.

PL

W artykule przedstawiono wpływ starzenia kondensatorów elektrolitycznych na poziom zaburzeń elektromagnetycznych generowanych przez układ podwyższający napięcie w oparciu o metody symulacyjne oraz cyfrowe przetwarzanie sygnału (filtracje Wienera). Wyniki przedstawiono w formie widm zaburzeń generowanych przez układ oraz transmitancji pomiędzy źródłem zaburzeń a zaburzeniami

3

Frequency Offset Compensation for OFDM Systems Using a Combined Autocorrelation and Wiener Filtering Scheme

Ramadan Ali A., Khanzada T. J., Omar A.

Journal of Telecommunications and Information Technology

|

2010

|

nr 1

40-47

EN

One of the orthogonal frequency division multiplexing (OFDM) system disadvantages is its sensitivity to frequency offset and phase noise, which lead to losing the orthogonality between the subcarriers and thereby degrade the system performance. In this paper a joint scheme for frequency offset and pilot-based channel estimation is introduced in which the frequency offset is first estimated using an autocorrelation method, and then is fined further by applying an iterative phase correction by means of pilot-based Wiener filtering method. In order to verify the capability of the estimation algorithm, the scheme has been implemented and tested using a real measurement system in a multipath indoor environment. The results show the algorithm capability of compensating for the frequency offset with different transmission and channel conditions.