Noise Reduction Of Speech Signals Research Articles

Exploration of Intelligent Transformation Path of Traditional Cultural and Creative Products Based on Internet of Things Technology

Abstract More and more modern technology is applied to traditional cultural and creative industries, which enhances the technicality and novelty of traditional cultural products, and the fusion of culture and modern technology profoundly changes people’s way of life and learning. This paper explores the Internet of Things (IoT) technology and the intelligent transformation process of cultural and creative products and constructs cultural and creative products that integrate intelligent voice series. Specifically, a speech recognition model is integrated into the design process of cultural and creative products, and the designed model is applied to the design of intelligent cultural and creative products by analyzing the Hidden Markov Model (HMM), proposing a solution to the shortcomings of the HMM model, and choosing to perform noise reduction of speech signals through the fixed beam algorithm. Based on the speech recognition model designed in this paper, an intelligent cultural and creative product with a speech recognition function is designed, taking the ‘owl wine container’ from the Shanxi Museum as an example. The regression equation of the audience’s satisfaction with the product is Y (satisfaction) = -0.000263 + 0.208X1 (practicality) + 0.265X2 (innovation) + 0.253X3 (culture) + 0.271X4 (interactivity) - 0.296X5 (fun). This paper’s intelligent cultural and creative products have a greater impact on satisfaction due to their innovativeness and interactive function.

Transformed wavelet applied in voice signals for noise reduction

This study presents a technique for noise reduction in speech signals adapting the wavelet transform by comparing it with the power spectral subtraction. To validate the results, segmented signal noise and Itakura Saito distance relationship were used. After analyzing the obtained results, we have verified that the technique based on Wavelet transform showed lower spectral distortion and, in some cases, a better signal to noise ratio.

Noise reduction in speech signal of Parkinson’s Disease (PD) patients using optimal variable stage cascaded adaptive filter configuration

In hands-free communications, including mobile phones, teleconferencing, and video conferencing, the ultimate aim is to obtain a noise-free signal. The adaptive filters that utilize the LMS adaptation algorithm are the best suited for speech signal de-noising among the existing speech signal enhancement techniques. LMS adaptive filter is preferred due to its low computational complexity and robustness, but it fails to simultaneously achieve a faster convergence speed and minimum steady-state MSE. This work introduces a novel cascaded adaptive filter structure for speech signal de-noising wherein the objective is to estimate the noise-free signal with high accuracy. The proposed optimal variable stage cascaded adaptive filter model utilizes a variable stage cascaded adaptive filter structure to estimate the noise-free signal, which is then employed to recover the clean signal with high accuracy. The proposed filter model is tested for reducing the noise from a normal speech signal taken from the NOIZEUS database and an impaired speech signal of Parkinson’s Disease affected patients taken from the MDVR-KCL dataset. The signals are corrupted by various stationary and non-stationary noise signals of different input SNR levels. The noisy signal is used to test the performance of the proposed optimal filter model. The signal de-noising performance of the proposed filter is evaluated in MSE, SNR, and ANR. The results have shown that the proposed filter model provides remarkable performance and an output SNR of 10–15 dB higher than the existing cascaded filter structures. Further, the proposed filter model employs LMS adaptive algorithm, offering a cost-effective and straightforward hardware implementation of ANC with improved accuracy.

Use of trainable wavelet transform with adaptive threshold filtering for noise reduction of speech signals

A method of noise reduction based on an adaptive threshold filtering over trainable wavelet transform was proposed. The restrictions on the trainable transform filter parameters were provided by a set of quadratic regularization terms. As an analog of the “hard” and “soft” threshold functions we used their smooth infinitely differentiable versions. The parameters of trainable wavelet transform, and threshold values were estimated by backpropagation and gradient-based optimization algorithm with an adaptive momentum estimation. Results of the proposed method were compared with an approach based on fixed discrete wavelet transform and non-adaptive global and level-depended threshold algorithms on the model problem. We used signal-to-noise ratio between suppressed and clean signals to numerically estimate the efficiency of noise reduction. We showed that the best results were obtained when the proposed trainable method with Daubechies 4 wavelet filters fine-tuning and adaptive level-dependent thresholding were applied.

Noise reduction in speech signals using adaptive independent component analysis (ICA) for hands free communication devices

This paper aims to remove the noise presents in speech signals during communication in all hands-free devices like mobile phone, video conferencing, teleconferencing conferencing etc. The existing noise reduction algorithms like an adaptive filter, time-varying and multiband adaptive gain control etc., have serious drawbacks. To enhance the algorithm for a better outcome an independent component analysis (ICA) based noise reduction is used. ICA is a statistical computational technique that divides the multisource signal into individual subcomponents. It is an active approach to cancel all of the ambient noise or a selective part of it without knowing the knowledge of the background noise. The adaptive nature of ICA in the proposed method makes the algorithm more robust in a real-time scenario. In the proposed method, the noisy speech signal is maximized by using kurtosis and negentropy cost functions of ICA to separate out the original speech signal from the noise. The simulations show that the proposed adaptive ICA method provides higher SNR compared to existing ICA methods and other conventional methods. Thus Adaptive ICA performs efficient noise cancellation in all real-time communication devices.

Comparative Study between the Discrete-Frequency Kalman Filtering and the Discrete-Time Kalman Filtering with Application in Noise Reduction in Speech Signals

This article aims to carry out a comparative study between discrete-time and discrete-frequency Kalman filters. In order to assess the performance of both methods for speech reconstruction, we measured the output segmental signal-to-noise ratio and the Itakura-Saito distance provided by each algorithm over 25 different voice signals. The results show that although the two algorithms performed very similarly regarding noise reduction, the discrete-time Kalman filter produced smaller spectral distortion on the estimated signals when compared with the discrete-frequency Kalman filter.

Correlation based Transient Removal Method for Speech Signal Enhancement

In this article, unwanted transients are specified by correlating the previous shade power standards and eliminated the detected transients. Various studies have been done on the autocorrelation based method to perform the noise reduction in speech signals. The speech signal is a one dimensional signal, for that the correlation may be with its delayed function. The proposed method uses recursive approach and the autocorrelation coefficient as a constraint or stopping criterion. The algorithm solves the transient problem of threshold for transient reduction and provides the alternative. The final simulation modelling shows the results.

Noise reduction of speech signals using time-varying and multi-band adaptive gain control for smart digital hearing protectors

In this paper, a single-channel speech enhancement algorithm based on non-linear and multi-band Adaptive Gain Control (AGC) is proposed. The algorithm requires neither Signal-to-Noise Ratio (SNR) nor noise parameters estimation. It reduces the background noise in the temporal domain rather than the spectral domain using a non-linear and automatically adjustable gain function for multi-band AGC. The gain function varies in time and is deduced from the temporal envelope of each frequency band to highly compress the frequency regions where noise is present and lightly compress the frequency regions where speech is present. Objective evaluation using the PESQ (Perceptual Evaluation of Speech Quality) metric shows that the proposed algorithm performs better than three benchmarks, namely: the spectral subtraction, the Wiener filter based on a priori SNR estimation and a band-pass modulation filtering algorithm. In addition, blind subjective tests show that the proposed algorithm introduces less musical noise compared to the benchmark algorithms and was preferred 78.8% of the time in terms of signal quality. The proposed algorithm is implemented in a miniature low power digital signal processor to validate its feasibility and complexity for smart hearing protection in noisy environments.

Transient noise reduction in speech signal with a modified long-term predictor

This article proposes an efficient median filter based algorithm to remove transient noise in a speech signal. The proposed algorithm adopts a modified long-term predictor (LTP) as the pre-processor of the noise reduction process to reduce speech distortion caused by the nonlinear nature of the median filter. This article shows that the LTP analysis does not modify to the characteristic of transient noise during the speech modeling process. Oppositely, if a short-term linear prediction (STP) filter is employed as a pre-processor, the enhanced output includes residual noise because the STP analysis and synthesis process keeps and restores transient noise components. To minimize residual noise and speech distortion after the transient noise reduction, a modified LTP method is proposed which estimates the characteristic of speech more accurately. By ignoring transient noise presence regions in the pitch lag detection step, the modified LTP successfully avoids being affected by transient noise. A backward pitch prediction algorithm is also adopted to reduce speech distortion in the onset regions. Experimental results verify that the proposed system efficiently eliminates transient noise while preserving desired speech signal.

Noise Reduction of Speech Signal using Wavelet Transform with Modified Universal Threshold

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.

Two Methods of Mechanical Noise Reduction of Recorded Speech During Phonation in an MRI device

The paper presents two methods of noise reduction of speech signal recorded in an MRI device during phonation for the human vocal tract modelling. The applied approach of noise speech signal cleaning is based on cepstral speech analysis and synthesis because the noise is mainly produced by gradient coils, has a mechanical character, and can be processed in spectral domain. Our first noise reduction method is using real cepstrum limitation and clipping the “peaks” corresponding to the harmonic frequencies of mechanical noise. The second method is coming out from substation of the short-time spectra of two signals recorded withal: the first includes speech and noise, and the second consists of noise only. The resulting speech quality was compared by spectrogram and mean periodogram methods.

Noise reduction of speech signals by running spectrum filtering

AbstractThis paper proposes a new noise reduction method intended for noise reduction in speech. The method combines running spectrum filtering (RSF) based on the different time variations of the power spectrum between speech and noise, and postprocessing to reduce musical noise. RSF is a filter which is realized in the modulation spectrum and can effectively reduce noise when applied to the running spectrum of speech. In this paper, it is shown that the segmental SNR of the speech with noise used in the experiment can be improved. A subjective listening experiment shows that the quality of speech degraded by noise is improved. © 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(14): 52–61, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.20529

Noise Reduction in Time Domain Using Referential Reconstruction

We present a novel approach for single-channel noise reduction of speech signals contaminated by additive noise. In this approach, the system requires speech samples to be uttered in advance by the same speaker as that of the input signal. Speech samples used in this method must have enough phonetic variety to reconstruct the input signal. In the proposed method, which we refer to as referential reconstruction, we have used a small database created from examples of speech, which will be called reference signals. Referential reconstruction uses an example-based approach, in which the objective is to find the candidate speech frame which is the most similar to the clean input frame without noise, although the input frame is contaminated with noise. When candidate frames are found, they become final outputs without any special processing. In order to find the candidate frames, a correlation coefficient is used as a similarity measure. Through automatic speech recognition experiments, the proposed method was shown to be effective, particularly for low-SNR speech signals corrupted with white noise or noise in high-frequency bands. Since the direct implementation of this method requires infeasible computational cost for searching through reference signals, a coarse-to-fine strategy is introduced in this paper.

A speech enhancement method using the sliding DFT

In this paper, we propose a novel noise reduction of speech signals using sliding DFT (SDFT) which is based on the spectral subtraction method. The spectral subtraction method reduces noise by subtracting the spectrum of noise estimated from an input signal and is a relatively simple and effective technique. We use SDFT to obtain the frequency spectra of speech signals. As is well known, to obtain the successive N-points output, SDFT requires only N times of complex multiplication, although the Fast Fourier Transform (FFT) requires Nlog2N times that. Thus SDFT is computationally simple as compared with FFT. The frame length, N, is determined based on the pitch period. In this paper, the pitch period is estimated by using an ideal low-pass filter and the analytic signal that is obtained from speech signals by the Hilbert converter. Finally, it is shown that the proposed method has good performance for speech enhancement.

Adaptive microphone‐array system for noise reduction

A new adaptive microphone‐array system for noise reduction (AMNOR system) is introduced. The AMNOR system detects the arrival directions of noise and forms a directional pattern possessing low sensitivities to those directions using a digital filtering technique. With pre‐informed data on the direction of desired signal source, the AMNOR system learns the noise arrival directions previously. Optimum filter coefficients are determined based on a new criterion, whose concept is to minimize output noise power while maintaining the degradation in the frequency response to the desired signal below the predetermined value. An algorithm for calculating the optimum filter is proposed. To confirm the effectiveness of the AMNOR system, experiments on the noise reduction processing were carried out in a room with a reverberation time of 0.4 s. A small circular microphone array (radius of 8.5 cm) with four microphone elements and four FIR filters with 16 taps were used. The convergence time of the algorithm at this experimental condition was 0.3 s. Improvement in SNR as a result of the AMNOR system by more than 15 dB in the frequency range of 300–3300 Hz. Superiority over the conventional LMS criterion for noise reduction of speech signals was also confirmed by subjective preference tests.