Hybrid Technique for Denoising Multi Environment Noise in Speech Processing
10 Jul 2018-pp 1-7
TL;DR: A hybrid technique for noise reduction in speech signals those are corrupted by noise in multi environments i.e. street, airport, car and train noises are processed by Gaussian window and kalman filter is introduced.
Abstract: In general noise control is critical issue in signal processing. Almost every signal that we are receiving at the receiver side of any communication system is somehow affected by noise. Noise is the unwanted part of the signal. In any communication system filtering is needed for rejecting all other unwanted frequencies present in the received signal and gives the desired signal. To denoising the different types noise signals requires different noise removing methods. This paper introducing a hybrid technique for noise reduction in speech signals those are corrupted by noise in multi environments i.e. street, airport, car and train noises are processed by Gaussian window and kalman filter. In order to access the accuracy of this combination of filters, the performance of this hybrid technique gives evaluation of both Mean Square Error and Peak Signal to Noise Ratio at the input to the corresponding values at the output of the system. The PSNR value of the proposed system for noise level of 10dB is affected by street noise is achieved 35.457339 as output. The results obtained by using this hybrid technique are better than the other techniques.
Citations
More filters
TL;DR: In this article, modified LMS algorithm is proposed which is used to denoise real-time speech signal and the proposed algorithm is made by combining general LMS and Diffusion least mean-square algorithm which increase the capabilities of adaptive filtering.
Abstract: In real time speech de-noising, adaptive filtering technique with variable length filters are used
which is used to track the noise characteristics and through those characteristics the filter equations are selected
The main features that attracted the use of the LMS algorithm are low computational complexity, proof of
convergence in stationary environment. In this paper, modified LMS algorithm is proposed which is used to denoise real time speech signal. The proposed algorithm is made by combining general LMS algorithm with
Diffusion least mean-square algorithm which increase the capabilities of adaptive filtering. The performance
parameter calculation shows that the proposed algorithm is effective to de-noise speech signal. A full
programming routine written in MATLAB software is provided for replications and further research
applications
7 citations
Journal Article•
03 Apr 2014-World Academy of Science, Engineering and Technology, International Journal of Mathematical, Computational, Physical, Electrical and Computer Engineering
TL;DR: This paper will do reconstruction of the speech signal, observed in additive background noise, using the Kalman filter technique to estimate the parameters of the Autoregressive Process (AR) in the state space model and the output speech signal obtained by the MATLAB.
Abstract: Revolutions Applications such as telecommunications, hands-free communications, recording, etc. which need at least one microphone, the signal is usually infected by noise and echo. The important application is the speech enhancement, which is done to remove suppressed noises and echoes taken by a microphone, beside preferred speech. Accordingly, the microphone signal has to be cleaned using digital signal processing DSP tools before it is played out, transmitted, or stored. Engineers have so far tried different approaches to improving the speech by get back the desired speech signal from the noisy observations. Especially Mobile communication, so in this paper will do reconstruction of the speech signal, observed in additive background noise, using the Kalman filter technique to estimate the parameters of the Autoregressive Process (AR) in the state space model and the output speech signal obtained by the MATLAB. The accurate estimation by Kalman filter on speech would enhance and reduce the noise then compare and discuss the results between actual values and estimated values which produce the reconstructed signals. Keywords—Autoregressive Process, Kalman filter, Matlab and Noise speech.
References
More filters
Book•
16 Jan 2001
TL;DR: Kalman Filtering: Theory and Practice Using MATLAB, Fourth Edition is an ideal textbook in advanced undergraduate and beginning graduate courses in stochastic processes and Kalman filtering and appropriate for self-instruction or review by practicing engineers and scientists who want to learn more about this important topic.
Abstract: The definitive textbook and professional reference on Kalman Filtering fully updated, revised, and expanded This book contains the latest developments in the implementation and application of Kalman filtering. Authors Grewal and Andrews draw upon their decades of experience to offer an in-depth examination of the subtleties, common pitfalls, and limitations of estimation theory as it applies to real-world situations. They present many illustrative examples including adaptations for nonlinear filtering, global navigation satellite systems, the error modeling of gyros and accelerometers, inertial navigation systems, and freeway traffic control. Kalman Filtering: Theory and Practice Using MATLAB, Fourth Edition is an ideal textbook in advanced undergraduate and beginning graduate courses in stochastic processes and Kalman filtering. It is also appropriate for self-instruction or review by practicing engineers and scientists who want to learn more about this important topic.
2,303 citations
"Hybrid Technique for Denoising Mult..." refers background in this paper
...Comparatively there are some advantages of kalman filter over other filter as a wiener filter as follows [13]....
[...]
TL;DR: It is argued that the Itakura-Saito and related distortions are well-suited computationally, mathematically, and intuitively for such applications.
Abstract: Several properties, interrelations, and interpretations are developed for various speech spectral distortion measures. The principle results are 1) the development of notions of relative strength and equivalence of the various distortion measures both in a mathematical sense corresponding to subjective equivalence and in a coding sense when used in minimum distortion or nearest neighbor speech processing systems; 2) the demonstration that the Itakura-Saito and related distortion measures possess a property similar to the triangle inequality when used in nearest neighbor systems such as quantization and cluster analysis; and 3) that the Itakura-Saito and normalized model distortion measures yield efficient computation algorithms for generalized centroids or minimum distortion points of groups or clusters of speech frames, an important computation in both classical cluster analysis techniques and in algorithms for optimal quantizer design. We also argue that the Itakura-Saito and related distortions are well-suited computationally, mathematically, and intuitively for such applications.
409 citations
"Hybrid Technique for Denoising Mult..." refers background in this paper
...This filter can remove the noise and distortion [10] based on the state space....
[...]
TL;DR: Here both hard and soft thresholding method performs better than hard thresholding at all input SNR levels and output SNR and MSE is calculated & compared using both types of thresholding methods.
Abstract: In this paper, Discrete-wavelet transform (DWT) based algorithm are used for speech signal denoising. Here both hard and soft thresholding are used for denoising. Analysis is done on noisy speech signal corrupted by babble noise at 0dB, 5dB, 10dB and 15dB SNR levels. Simulation & results are performed in MATLAB 7.10.0 (R2010a). Output SNR (Signal to Noise Ratio) and MSE (Mean Square Error) is calculated & compared using both types of thresholding methods. Soft thresholding method performs better than hard thresholding at all input SNR levels. Hard thresholding shows a maximum of 21.79 dB improvement whereas soft thresholding shows a maximum of 35.16 dB improvement in output SNR. General Terms Thresholding, multi-resolution analysis, wavelet.
78 citations
"Hybrid Technique for Denoising Mult..." refers methods in this paper
...Wavelet transforming techniques are also used for denoising the speech signal affected by noise [8]....
[...]
TL;DR: Results showed that using one-fourth overlapped data buffers with 128 points Hanning windows and no frames averaging leads to the best performance in removing noise from the noisy speech.
Abstract: Spectral
subtraction is used in this research as a method to remove noise from noisy
speech signals in the frequency domain. This method consists of computing the
spectrum of the noisy speech using the Fast Fourier Transform (FFT) and
subtracting the average magnitude of the noise spectrum from the noisy speech
spectrum. We applied spectral subtraction to the speech signal “Real graph”. A
digital audio recorder system embedded in a personal computer was used to
sample the speech signal “Real graph” to which we digitally added vacuum
cleaner noise. The noise removal algorithm was implemented using Matlab
software by storing the noisy speech data into Hanning time-widowed
half-overlapped data buffers, computing the corresponding spectrums using the
FFT, removing the noise from the noisy speech, and reconstructing the speech
back into the time domain using the inverse Fast Fourier Transform (IFFT). The
performance of the algorithm was evaluated by calculating the Speech to Noise Ratio
(SNR). Frame averaging was introduced
as an optional technique that could improve the SNR. Seventeen different configurations with various lengths of the
Hanning time windows, various degrees of data buffers overlapping, and various
numbers of frames to be averaged were investigated in view of improving the SNR. Results showed that using
one-fourth overlapped data buffers with 128 points Hanning windows and no
frames averaging leads to the best performance in removing noise from the noisy
speech.
35 citations
TL;DR: The most currently used methods of speech coding are reviewed, including reviewing the basic attributes of these coders, the methods used for coding and some of the most important speech coding standards.
Abstract: Digital speech coding is used in a wide variety of every day applications that the ordinary person takes for granted, such as network wireline and cellular telephony and telephone answering machines. This article reviews some of the most currently used methods of speech coding. This includes reviewing the basic attributes of these coders, the methods used for coding and some of the most important speech coding standards. It also reviews the methods used to realize digital speech coders, especially those for implementing these coders in a cost effective manner.
4 citations