A Single-Channel Noise Reduction Filtering/Smoothing Technique in the Time Domain
13 Apr 2018-pp 636-640
TL;DR: Simulation results reveal that the developed method can produce better noise reduction performance, i.e., higher gains in the perceptual-evaluation-of-speech-quality (PESQ) score, than the traditional methods without smoothing.
Abstract: In this paper, we present a single-channel smoothing-and-filtering technique for noise reduction in the time domain. Unlike traditional noise reduction methods, which directly apply a noise reduction filter to the noisy signal, the developed technique achieves noise reduction in two steps. It first applies a time smoothing window to the noisy signal, which, on the one hand, can help reduce high frequency noise and, on the other hand, can help leverage the correlation between successive signal samples. A noise reduction filter is then applied to the smoothed noisy signal to estimate the speech signal of interest. Three optimal and suboptimal noise reduction filters are derived, including the Wiener, maximum signal-to-noise-ratio (SNR), and tradeoff filters. Simulation results reveal that the developed method can produce better noise reduction performance, i.e., higher gains in the perceptual-evaluation-of-speech-quality (PESQ) score, than the traditional methods without smoothing.
Citations
More filters
20 Apr 2020
TL;DR: In this article, the authors proposed an efficient, robust, and reconfigurable technique to suppress various types of noises for any sampling rate, which significantly enhances the speech transmission index (STI), speech intelligibility (SI), signal-to-noise ratio (SNR), and subjective listening experience.
Abstract: The paper proposes an efficient, robust, and reconfigurable technique to suppress various types of noises for any sampling rate. The theoretical analyses, subjective and objective test results show that the proposed noise suppression (NS) solution significantly enhances the speech transmission index (STI), speech intelligibility (SI), signal-to-noise ratio (SNR), and subjective listening experience. The STI and SI consists of 5 levels, i.e., bad, poor, fair, good, and excellent. The most common noisy condition is of SNR ranging from -5 to 8 dB. For the input SNR between -5 and 2.5 dB, the proposed NS improves the STI and SI from "fair" to "good". For the input SNR between 2.5 to 8 dB, the STI and SI are improved from "good" to "excellent" by the proposed NS. The proposed NS can be adopted in both capture and playback paths for voice over internet protocol, voice-trigger, and automatic speech recognition applications.
2 citations
17 Jun 2022
TL;DR: In this article , an improved wavelet thresholding function was proposed and applied in speech signal denoising, which can not only improve the signal-to-noise ratio (SNR) of the voice signal, but also largely avoid the distortion of voice signal.
Abstract: Voice signal is disturbed by environmental noise during recording, which reduces the clarity of voice signal and affects the acquisition of useful signals. The wavelet threshold de noising method is widely used in the field of signal de noising. However, the hard/soft thresholding function in traditional wavelet transform has some problems such as discontinuity and fixed deviation when filtering. Therefore, an improved wavelet thresholding function method is proposed and applied in speech signal denoising. Through theoretical analysis and simulation, the results show that the improved wavelet threshold denoising algorithm can not only improve the signal-to-noise ratio (SNR) of the voice signal, but also largely avoid the distortion of the voice signal.
Posted Content•
TL;DR: The theoretical analyses, subjective and objective test results show that the proposed noise suppression (NS) solution significantly enhances the speech transmission index (STI), speech intelligibility (SI), signal-to-noise ratio (SNR), and subjective listening experience.
Abstract: The paper proposes an efficient, robust, and reconfigurable technique to suppress various types of noises for any sampling rate. The theoretical analyses, subjective and objective test results show that the proposed noise suppression (NS) solution significantly enhances the speech transmission index (STI), speech intelligibility (SI), signal-to-noise ratio (SNR), and subjective listening experience. The STI and SI consists of 5 levels, i.e., bad, poor, fair, good, and excellent. The most common noisy condition is of SNR ranging from -5 to 8 dB. For the input SNR between -5 and 2.5 dB, the proposed NS improves the STI and SI from "fair" to "good". For the input SNR between 2.5 to 8 dB, the STI and SI are improved from "good" to "excellent" by the proposed NS. The proposed NS can be adopted in both capture and playback paths for voice over internet protocol, voice-trigger, and automatic speech recognition applications.
Cites methods from "A Single-Channel Noise Reduction Fi..."
...We have run 72 test cases by covering the following test conditions: (1) two input SNRs: 6 dB and 12 dB, (2) two speech-levels at mouth reference point: 89 and 95 dBC, (3) two distance settings between device-under-test (DUT) and head-and-torso-simulator (HATS): 1 meter and 4 meters, (4) 9 types of noises: air condition noise, café noise, fan noise, living-room noise, office noise, pink noise, Pub noise, rain noise, and rock musical noise....
[...]
References
More filters
TL;DR: A stand-alone noise suppression algorithm that resynthesizes a speech waveform and can be used as a pre-processor to narrow-band voice communications systems, speech recognition systems, or speaker authentication systems.
Abstract: A stand-alone noise suppression algorithm is presented for reducing the spectral effects of acoustically added noise in speech. Effective performance of digital speech processors operating in practical environments may require suppression of noise from the digital wave-form. Spectral subtraction offers a computationally efficient, processor-independent approach to effective digital speech analysis. The method, requiring about the same computation as high-speed convolution, suppresses stationary noise from speech by subtracting the spectral noise bias calculated during nonspeech activity. Secondary procedures are then applied to attenuate the residual noise left after subtraction. Since the algorithm resynthesizes a speech waveform, it can be used as a pre-processor to narrow-band voice communications systems, speech recognition systems, or speaker authentication systems.
4,862 citations
"A Single-Channel Noise Reduction Fi..." refers background in this paper
...A great deal of efforts have been devoted to addressing this problem in the literature [9, 10, 11] and various methods have been proposed, including subspace methods [12, 13, 14], optimal filtering [3, 4, 15], statistical approach [16], spectral subtraction type of techniques [17, 18], and data driven based machine learning methods [19, 20], etc....
[...]
Book•
07 Jun 2007
TL;DR: Clear and concise, this book explores how human listeners compensate for acoustic noise in noisy environments and suggests steps that can be taken to realize the full potential of these algorithms under realistic conditions.
Abstract: With the proliferation of mobile devices and hearing devices, including hearing aids and cochlear implants, there is a growing and pressing need to design algorithms that can improve speech intelligibility without sacrificing quality. Responding to this need, Speech Enhancement: Theory and Practice, Second Edition introduces readers to the basic problems of speech enhancement and the various algorithms proposed to solve these problems. Updated and expanded, this second edition of the bestselling textbook broadens its scope to include evaluation measures and enhancement algorithms aimed at improving speech intelligibility. Fundamentals, Algorithms, Evaluation, and Future Steps Organized into four parts, the book begins with a review of the fundamentals needed to understand and design better speech enhancement algorithms. The second part describes all the major enhancement algorithms and, because these require an estimate of the noise spectrum, also covers noise estimation algorithms. The third part of the book looks at the measures used to assess the performance, in terms of speech quality and intelligibility, of speech enhancement methods. It also evaluates and compares several of the algorithms. The fourth part presents binary mask algorithms for improving speech intelligibility under ideal conditions. In addition, it suggests steps that can be taken to realize the full potential of these algorithms under realistic conditions. Whats New in This Edition Updates in every chapter A new chapter on objective speech intelligibility measures A new chapter on algorithms for improving speech intelligibility Real-world noise recordings (on accompanying CD) MATLAB code for the implementation of intelligibility measures (on accompanying CD) MATLAB and C/C++ code for the implementation of algorithms to improve speech intelligibility (on accompanying CD) Valuable Insights from a Pioneer in Speech Enhancement Clear and concise, this book explores how human listeners compensate for acoustic noise in noisy environments. Written by a pioneer in speech enhancement and noise reduction in cochlear implants, it is an essential resource for anyone who wants to implement or incorporate the latest speech enhancement algorithms to improve the quality and intelligibility of speech degraded by noise. Includes a CD with Code and Recordings The accompanying CD provides MATLAB implementations of representative speech enhancement algorithms as well as speech and noise databases for the evaluation of enhancement algorithms.
2,269 citations
"A Single-Channel Noise Reduction Fi..." refers background in this paper
...Noise reduction is the process of recovering a clean speech signal of interest from microphone observations (either a single microphone or multiple microphones) corrupted by additive noise [1, 2]....
[...]
...SIGNAL MODEL AND PROBLEM FORMULATION In the noise reduction problem considered in this paper, the noisy observation or microphone signal is given by [1], [2]...
[...]
01 Feb 1993
2,164 citations
"A Single-Channel Noise Reduction Fi..." refers methods in this paper
...The clean speech signals (consisting of 20 sentences with 10 from a male speaker and the other 10 from a female speaker) are taken from the TIMIT database [7]....
[...]
TL;DR: The proposed DNN approach can well suppress highly nonstationary noise, which is tough to handle in general, and is effective in dealing with noisy speech data recorded in real-world scenarios without the generation of the annoying musical artifact commonly observed in conventional enhancement methods.
Abstract: In contrast to the conventional minimum mean square error (MMSE)-based noise reduction techniques, we propose a supervised method to enhance speech by means of finding a mapping function between noisy and clean speech signals based on deep neural networks (DNNs). In order to be able to handle a wide range of additive noises in real-world situations, a large training set that encompasses many possible combinations of speech and noise types, is first designed. A DNN architecture is then employed as a nonlinear regression function to ensure a powerful modeling capability. Several techniques have also been proposed to improve the DNN-based speech enhancement system, including global variance equalization to alleviate the over-smoothing problem of the regression model, and the dropout and noise-aware training strategies to further improve the generalization capability of DNNs to unseen noise conditions. Experimental results demonstrate that the proposed framework can achieve significant improvements in both objective and subjective measures over the conventional MMSE based technique. It is also interesting to observe that the proposed DNN approach can well suppress highly nonstationary noise, which is tough to handle in general. Furthermore, the resulting DNN model, trained with artificial synthesized data, is also effective in dealing with noisy speech data recorded in real-world scenarios without the generation of the annoying musical artifact commonly observed in conventional enhancement methods.
1,250 citations
"A Single-Channel Noise Reduction Fi..." refers background in this paper
...A great deal of efforts have been devoted to addressing this problem in the literature [9, 10, 11] and various methods have been proposed, including subspace methods [12, 13, 14], optimal filtering [3, 4, 15], statistical approach [16], spectral subtraction type of techniques [17, 18], and data driven based machine learning methods [19, 20], etc....
[...]
26 Jun 1979
TL;DR: An overview of the variety of techniques that have been proposed for enhancement and bandwidth compression of speech degraded by additive background noise is provided to suggest a unifying framework in terms of which the relationships between these systems is more visible and which hopefully provides a structure which will suggest fruitful directions for further research.
Abstract: Over the past several years there has been considerable attention focused on the problem of enhancement and bandwidth compression of speech degraded by additive background noise. This interest is motivated by several factors including a broad set of important applications, the apparent lack of robustness in current speech-compression systems and the development of several potentially promising and practical solutions. One objective of this paper is to provide an overview of the variety of techniques that have been proposed for enhancement and bandwidth compression of speech degraded by additive background noise. A second objective is to suggest a unifying framework in terms of which the relationships between these systems is more visible and which hopefully provides a structure which will suggest fruitful directions for further research.
1,236 citations
"A Single-Channel Noise Reduction Fi..." refers background in this paper
...Some of the aforementioned methods conduct noise reduction in the time domain, while others operate in transform domains [21], among which the frequency domain or short-time-Fourier-transform domain is widely adopted [9, 10, 11, 22]....
[...]
...A great deal of efforts have been devoted to addressing this problem in the literature [9, 10, 11] and various methods have been proposed, including subspace methods [12, 13, 14], optimal filtering [3, 4, 15], statistical approach [16], spectral subtraction type of techniques [17, 18], and data driven based machine learning methods [19, 20], etc....
[...]