Download or read book Speech Enhancement Using an Iterative Posterior NMF written by Sunnydayal Vanambathina and published by . This book was released on 2020 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Over the years, miscellaneous methods for speech enhancement have been proposed, such as spectral subtraction (SS) and minimum mean square error (MMSE) estimators. These methods do not require any prior knowledge about the speech and noise signals nor any training stage beforehand, so they are highly flexible and allow implementation in various situations. However, these algorithms usually assume that the noise is stationary and are thus not good at dealing with nonstationary noise types, especially under low signal-to-noise (SNR) conditions. To overcome the drawbacks of the above methods, nonnegative matrix factorization (NMF) is introduced. NMF approach is more robust to nonstationary noise. In this chapter, we are actually interested in the application of speech enhancement using NMF approach. A speech enhancement method based on regularized nonnegative matrix factorization (NMF) for nonstationary Gaussian noise is proposed. The spectral components of speech and noise are modeled as Gamma and Rayleigh, respectively. We propose to adaptively estimate the sufficient statistics of these distributions to obtain a natural regularization of the NMF criterion.

Download or read book New Frontiers in Brain written by Nawaz Mohamudally and published by BoD – Books on Demand. This book was released on 2020-02-26 with total page 144 pages. Available in PDF, EPUB and Kindle. Book excerpt: Brain-Computer Interface (BCI) sounds comparable to plugging a USB cable into a human brain with a laptop and accessing brain information. However, it is not as simple as it sounds. BCI is a multidisciplinary discipline with an exponential progress parallel to and with Artificial Intelligence for the past decades. Initially started with the Electroencephalography (EEG) analysis, BCI offers practical applications for cortical physiology today. Although BCI outcomes are more perceptible in medicine such as cognitive assessment, neurofeedback, and neuroprosthetic implants, it opens up amazing avenues for the business community through machine learning and robotics. Thought-to-text is one example of a hot topic in BCI. So, it is quite predictable to see BCI for individual usage given the current affordability of platforms for less technologically savvy users as well as BCI integrated within office automation productivity tools. The current trend is towards vulgarization for businesses benefits, by extension to the society at large. Thus, the interest in preparing a book on BCI. This book aims to compile and disseminate the latest research findings and best practices on how BCI is expanding the frontiers of knowledge in clinical practices, on the brain itself, and the underlying technologies.

Download or read book Speech Enhancement Using Training based Non negative Matrix Factorization Techniques written by Hanwook Chung and published by . This book was released on 2018 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: "In this thesis, we develop novel training-based non-negative matrix factorization (NMF) algorithms for single and multi-channel speech enhancement.After introducing the problem and reviewing background material, we first present a regularized NMF algorithm with Gaussian mixtures and masking model for single-channel speech enhancement. The proposed framework seeks to exploit the statistical properties of the clean speech and noise. This is accomplished by including the log-likelihood functions (LLF) of the clean speech and noise magnitude spectra, based on Gaussian mixture models (GMM), as the regularization terms in the NMF cost function. Moreover, we incorporate the masking effects of the human auditory system to further improve the enhanced speech quality.Second, we introduce a training and compensation algorithm of the class-conditioned NMF model for single-channel speech enhancement. The main goal is to reduce the residual noise components that have features similar to the speech. To this end, during the training stage, the basis vectors of different sources are obtained in a way that prevents them from representing each other, based on the concept of classification. Another goal is to handle the mismatch between the characteristics of the training and test data. This is accomplished by employing extra free basis vectors during the enhancement stage to capture the features which are not included in the training data.Finally, we present a novel multi-channel speech enhancement algorithm based on a Bayesian NMF model. Essentially, we consider the Poisson-distributed latent variable model for multi-channel NMF. During the training stage, the NMF parameters are estimated from the tensor-based training data. During the enhancement stage, the clean speech signal is estimated via the NMF-based minimum variance distortionless response (MVDR) beamforming technique. To this end, the source locations are estimated by observing the spatial output power of a delay-and-sum (DS) beamformer applied to the NMF-based pre-processed noisy speech signal.For each one of the above algorithms, objective experiments are carried out for different combinations of speaker, noise types and signal-to-noise ratio. The results show that the proposed methods provide better speech enhancement performance than the selected benchmark algorithms under considered test conditions." --

Download or read book Machine Learning Image Processing Network Security and Data Sciences written by Rajesh Doriya and published by Springer Nature. This book was released on 2023-01-01 with total page 886 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book constitutes the refereed proceedings of the Third International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2021. The papers are organized according to the following topical sections: data science and big data; image processing and computer vision; machine learning and computational intelligence; network and cybersecurity. This book aims to develop an understanding of image processing, networks, and data modeling by using various machine learning algorithms for a wide range of real-world applications. In addition to providing basic principles of data processing, this book teaches standard models and algorithms for data and image analysis.

Download or read book Speech Enhancement written by Jacob Benesty and published by Elsevier. This book was released on 2014-01-04 with total page 143 pages. Available in PDF, EPUB and Kindle. Book excerpt: Speech enhancement is a classical problem in signal processing, yet still largely unsolved. Two of the conventional approaches for solving this problem are linear filtering, like the classical Wiener filter, and subspace methods. These approaches have traditionally been treated as different classes of methods and have been introduced in somewhat different contexts. Linear filtering methods originate in stochastic processes, while subspace methods have largely been based on developments in numerical linear algebra and matrix approximation theory. This book bridges the gap between these two classes of methods by showing how the ideas behind subspace methods can be incorporated into traditional linear filtering. In the context of subspace methods, the enhancement problem can then be seen as a classical linear filter design problem. This means that various solutions can more easily be compared and their performance bounded and assessed in terms of noise reduction and speech distortion. The book shows how various filter designs can be obtained in this framework, including the maximum SNR, Wiener, LCMV, and MVDR filters, and how these can be applied in various contexts, like in single-channel and multichannel speech enhancement, and in both the time and frequency domains. - First short book treating subspace approaches in a unified way for time and frequency domains, single-channel, multichannel, as well as binaural, speech enhancement - Bridges the gap between optimal filtering methods and subspace approaches - Includes original presentation of subspace methods from different perspectives

Download or read book Fundamentals of Speech Enhancement written by Jacob Benesty and published by Springer. This book was released on 2018-02-09 with total page 112 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book presents and develops several important concepts of speech enhancement in a simple but rigorous way. Many of the ideas are new; not only do they shed light on this old problem but they also offer valuable tips on how to improve on some well-known conventional approaches. The book unifies all aspects of speech enhancement, from single channel, multichannel, beamforming, time domain, frequency domain and time–frequency domain, to binaural in a clear and flexible framework. It starts with an exhaustive discussion on the fundamental best (linear and nonlinear) estimators, showing how they are connected to various important measures such as the coefficient of determination, the correlation coefficient, the conditional correlation coefficient, and the signal-to-noise ratio (SNR). It then goes on to show how to exploit these measures in order to derive all kinds of noise reduction algorithms that can offer an accurate and versatile compromise between noise reduction and speech distortion.

Download or read book Speech Enhancement written by Philipos C. Loizou and published by CRC Press. This book was released on 2013-02-25 with total page 715 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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 pr

Download or read book Recent Advances in Signal Processing written by Ashraf Zaher and published by IntechOpen. This book was released on 2009-11-01 with total page 560 pages. Available in PDF, EPUB and Kindle. Book excerpt: The signal processing task is a very critical issue in the majority of new technological inventions and challenges in a variety of applications in both science and engineering fields. Classical signal processing techniques have largely worked with mathematical models that are linear, local, stationary, and Gaussian. They have always favored closed-form tractability over real-world accuracy. These constraints were imposed by the lack of powerful computing tools. During the last few decades, signal processing theories, developments, and applications have matured rapidly and now include tools from many areas of mathematics, computer science, physics, and engineering. This book is targeted primarily toward both students and researchers who want to be exposed to a wide variety of signal processing techniques and algorithms. It includes 27 chapters that can be categorized into five different areas depending on the application at hand. These five categories are ordered to address image processing, speech processing, communication systems, time-series analysis, and educational packages respectively. The book has the advantage of providing a collection of applications that are completely independent and self-contained; thus, the interested reader can choose any chapter and skip to another without losing continuity.

Download or read book Dual channel Iterative Speech Enhancement with Constraints Based on the Auditory Process written by S. Nandkumar and published by . This book was released on 1993 with total page 354 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Speech Enhancement written by Philipos C. Loizou and published by CRC Press. This book was released on 2007-06-07 with total page 640 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book covers traditional speech enhancement algorithms, such as spectral subtraction and Wiener filtering algorithms as well as state-of-the-art algorithms including minimum mean-squared error algorithms that incorporate signal-presence uncertainty and subspace algorithms that incorporate psychoacoustic models. The coverage includes objective and subjective measures used to evaluate speech quality and intelligibility. Divided into three parts, the book presents the digital-signal processing and speech signal fundamentals needed to understand speech enhancement algorithms, the various classes of speech enhancement algorithms proposed over the last two decades, and the methods and measures used to evaluate the performance of speech enhancement algorithms.

Download or read book Speech Enhancement Using Sparse Representation Methods written by Tak Wai Shen and published by . This book was released on 2015 with total page 162 pages. Available in PDF, EPUB and Kindle. Book excerpt: While the wavelet transform can sparsely describe the sudden changes in a speech power spectrum, it misses the periodic nature of speech signals which is an important feature in speech enhancement. For the second part of this study, a new speech enhancement method based on the sparsity of speeches in the cepstral domain is investigated. It is known that voiced speeches have a quasi-periodic nature that allows them to be compactly represented in the cepstral domain. It is a distinctive feature compared with noises. Recently, the temporal cepstrum smoothing (TCS) algorithm was proposed and was shown to be effective for speech enhancement in non-stationary noise environments. However, the missing of an automatic parameter updating mechanism limits its adaptability to noisy speeches with abrupt changes in SNR across time frames or frequency components. In this part, an improved speech enhancement algorithm based on a novel EM framework is proposed. The new algorithm starts with the traditional TCS method which gives the initial guess of the periodogram of the clean speech. It is then applied to an L1 norm regularizer in the M-step of the EM framework to estimate the true power spectrum of the original speech. It in turn enables the estimation of the a-priori SNR and is used in the E-step, which is indeed an MMSE-LSA gain function, to refine the estimation of the clean speech periodogram. The M-step and E-step iterate alternately until converged. A notable improvement of the proposed algorithm over the traditional TCS method is its adaptability to the changes (even abrupt changes) in SNR of the noisy speech. Performance of the proposed algorithm is evaluated using standard measures based on a large set of speech and noise signals. Evaluation results show that a significant improvement is achieved compared to conventional approaches. The above shows that obtaining the sparse representation of speeches is one of the keys for designing an efficient speech enhancement algorithm. One obvious question then arises if the ceptrum is the best representation of speeches as far as the sparsity is concerned. To answer this question, we further investigate a new sparse representation based speech enhancement algorithm with the transform kernel trained based on the dictionary learning method. It is known that the dictionary learning method allows the design of a transform kernel with the emphasis of sparsity in the transform domain. When applying to speech enhancement, it allows a speech to be represented by very few significant transform coefficients. In practice, the overcomplete dictionary of the clean speech signal is trained by an extended K-SVD algorithm in the log power spectra domain. The batch LARS with Coherence Criterion (LARC) method is used to reconstruct the log power spectra of the clean speech. And a new stopping criterion is proposed for the iterative speech enhancement process in order to adapt to various background noise environment. In addition, a modified two-step noise reduction with MMSE-LSA filtering is applied which solves the bias problem of the estimated a priori SNR. A notable improvement of the proposed algorithm over the traditional speech enhancement method is its adaptability to the changes in SNR of the noisy speech. Performance of the proposed algorithm is evaluated using standard measures based on a large set of speech and noise signals. Evaluation results show that a significant improvement is achieved compared to the traditional approaches especially when the noises are not totally random but have certain structure in the frequency domain.

Download or read book Speech Enhancement and Source Separation Using Probabilistic Models written by Jiucang Hao and published by . This book was released on 2008 with total page 117 pages. Available in PDF, EPUB and Kindle. Book excerpt: Statistical signal processing has been very successful. We proposed novel probabilistic models and developed efficient algorithms for two important problems: speech enhancement and source separation. Part I focused on the speech enhancement. We developed two models with efficient algorithms. The first one assumed a Gaussian Mixture Model (GMM) in the log-spectral domain for speech prior which was trained by expectation maximization (EM) algorithm. Three approximations were employed to enhance the computational efficiency. The Laplace method estimated the signal by computing the mode of the posterior distribution, either in the frequency domain or in the log-spectrum domain. The Gaussian approximation converted the GMM in the log-spectrum domain into a GMM in the frequency domain by minimizing the KL-divergence. It provided an efficient gain and noise spectrum estimation with the EM algorithm. The second one used a Gaussian scale mixture model (GSMM) as speech prior. This model specified a stochastic dependency between the log-spectra and the frequency components which can be estimated simultaneously with GSMM. The algorithms for training the model and signal estimation were developed. All these algorithms were evaluated by applying them to enhance the speeches corrupted by the speech shaped noise (SSN). The experimental results demonstrated that the proposed algorithms improved the signal-to-noise ratio and lowered the word recognition error rate. In part II, a novel probabilistic framework based on Independent Vector Analysis (IVA) was proposed to separate the convolutive mixture of sources. IVA assumed a multidimensional GMM for the source priors. The joint modeling of all frequency bins originating from the same source prevented the permutation disorder that associated with independent component analysis (ICA). The GMM source priors could adapt to the statistics of the sources and enable IVA to separate different type of signals. We developed EM algorithms for both the noiseless case and noisy case. For noiseless case, an online algorithm was developed to handle non-stationary environments. For noisy case, noise reduction was achieved together with the separation processes. The algorithms were evaluated by applying them to separate the mixtures of speech and music. The experimental results showed improved performance over other algorithms.

Download or read book Speech Enhancement Using Nonnegative Matrix Factorization and Hidden Markov Models written by and published by . This book was released on 2013 with total page 52 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Single Channel Speech Enhancement Using Kalman Filter written by Sujan Kumar Roy and published by . This book was released on 2016 with total page 108 pages. Available in PDF, EPUB and Kindle. Book excerpt: The quality and intelligibility of speech conversation are generally degraded by the surrounding noises. The main objective of speech enhancement (SE) is to eliminate or reduce such disturbing noises from the degraded speech. Various SE methods have been proposed in literature. Among them, the Kalman filter (KF) is known to be an efficient SE method that uses the minimum mean square error (MMSE). However, most of the conventional KF based speech enhancement methods need access to clean speech and additive noise information for the state-space model parameters, namely, the linear prediction coefficients (LPCs) and the additive noise variance estimation, which is impractical in the sense that in practice, we can access only the noisy speech. Moreover, it is quite difficult to estimate these model parameters efficiently in the presence of adverse environmental noises. Therefore, the main focus of this thesis is to develop single channel speech enhancement algorithms using Kalman filter, where the model parameters are estimated in noisy conditions. Depending on these parameter estimation techniques, the proposed SE methods are classified into three approaches based on non-iterative, iterative, and sub-band iterative KF. In the first approach, a non-iterative Kalman filter based speech enhancement algorithm is presented, which operates on a frame-by-frame basis. In this proposed method, the state-space model parameters, namely, the LPCs and noise variance, are estimated first in noisy conditions. For LPC estimation, a combined speech smoothing and autocorrelation method is employed. A new method based on a lower-order truncated Taylor series approximation of the noisy speech along with a difference operation serving as high-pass filtering is introduced for the noise variance estimation. The non-iterative Kalman filter is then implemented with these estimated parameters effectively. In order to enhance the SE performance as well as parameter estimation accuracy in noisy conditions, an iterative Kalman filter based single channel SE method is proposed as the second approach, which also operates on a frame-by-frame basis. For each frame, the state-space model parameters of the KF are estimated through an iterative procedure. The Kalman filtering iteration is first applied to each noisy speech frame, reducing the noise component to a certain degree. At the end of this first iteration, the LPCs and other state-space model parameters are re-estimated using the processed speech frame and the Kalman filtering is repeated for the same processed frame. This iteration continues till the KF converges or a maximum number of iterations is reached, giving further enhanced speech frame. The same procedure will repeat for the following frames until the last noisy speech frame being processed. For further improving the speech enhancement performance, a sub-band iterative Kalman filter based SE method is also proposed as the third approach. A wavelet filter-bank is first used to decompose the noisy speech into a number of sub-bands. To achieve the best trade-off among the noise reduction, speech intelligibility and computational complexity, a partial reconstruction scheme based on consecutive mean squared error (CMSE) is proposed to synthesize the low-frequency (LF) and highfrequency (HF) sub-bands such that the iterative KF is employed only to the partially reconstructed HF sub-band speech. Finally, the enhanced HF sub-band speech is combined with the partially reconstructed LF sub-band speech to reconstruct the full-band enhanced speech. Experimental results have shown that the proposed KF based SE methods are capable of reducing adverse environmental noises for a wide range of input SNRs, and the overall performance of the proposed methods in terms of different evaluation metrics is superior to some existing state-of-the art SE methods.

Download or read book Multi channel Speech Enhancement by Regularized Optimization written by Meng Yu and published by . This book was released on 2012 with total page 123 pages. Available in PDF, EPUB and Kindle. Book excerpt: Speech enhancement aims to eliminate noise and unexpected interferences that degrade speech quality and intelligibility in realistic listening situations. It is an indispensible technique in telecommunication and assistive listening devices such as hands-free mobile phones and hearing aids. Though a lot of research has been done in this area, only a limited number of methods can be eective in both real time and real world conditions. Diculties include noise types (incoherent, coherent, diuse), a-priori unknown number of noise sources, mobility of source locations, room reverberations, and non-stationarity. In this thesis, we focus on speech enhancement by suppressing coherent noise and reverberation. Classical speech enhancement methods rely on data from a single microphone. Spectral estimation methods, such as spectral subtraction, Wiener ltering and subspace method, are most widely used. In recent years, microphone array techniques have been developed and recognized as more powerful and promising solutions. Crosschannel cancellation is incorporated in the thesis to resolve the spatial dierence between channels, which helps to blindly identify channel impulse responses and forms the constraints between channels as well. L1 regularized minimization framework is incorporated to speech signal processing, with the regularization applied on channel impulse responses and speech spectrogram, respectively. The over-tting problem in the lter and spectrogram estimation is overcome by the sparsity regularization. Split Bregman method is used to derive the updating rules for speech enhancement in the time domain, while in the spectral domain non-negativity is applied on the spectrogram magnitude of speech signal and impulse response. Therefore, the proposed speech dereverberation method is solved under a constrained non-negative matrix factorization framework (NMF) in the spectrogram magnitude domain. The thesis is organized as follows. In chapter 1, the mathematical frameworks on L1 minimization and NMF are introduced, respectively. Under l1 minimization framework, chapter 2, 3 and 4 present the convex speech enhancement model, musical noise reduction and overlapping speech detection method, respectively. The multichannel speech dereverberation method is presented in chapter 5 under a constrained NMF framework. The thesis is concluded in chapter 6.

Download or read book Audio Source Separation and Speech Enhancement written by Emmanuel Vincent and published by John Wiley & Sons. This book was released on 2018-10-22 with total page 517 pages. Available in PDF, EPUB and Kindle. Book excerpt: Learn the technology behind hearing aids, Siri, and Echo Audio source separation and speech enhancement aim to extract one or more source signals of interest from an audio recording involving several sound sources. These technologies are among the most studied in audio signal processing today and bear a critical role in the success of hearing aids, hands-free phones, voice command and other noise-robust audio analysis systems, and music post-production software. Research on this topic has followed three convergent paths, starting with sensor array processing, computational auditory scene analysis, and machine learning based approaches such as independent component analysis, respectively. This book is the first one to provide a comprehensive overview by presenting the common foundations and the differences between these techniques in a unified setting. Key features: Consolidated perspective on audio source separation and speech enhancement. Both historical perspective and latest advances in the field, e.g. deep neural networks. Diverse disciplines: array processing, machine learning, and statistical signal processing. Covers the most important techniques for both single-channel and multichannel processing. This book provides both introductory and advanced material suitable for people with basic knowledge of signal processing and machine learning. Thanks to its comprehensiveness, it will help students select a promising research track, researchers leverage the acquired cross-domain knowledge to design improved techniques, and engineers and developers choose the right technology for their target application scenario. It will also be useful for practitioners from other fields (e.g., acoustics, multimedia, phonetics, and musicology) willing to exploit audio source separation or speech enhancement as pre-processing tools for their own needs.

Download or read book Robust Automatic Speech Recognition written by Jinyu Li and published by Academic Press. This book was released on 2015-10-30 with total page 308 pages. Available in PDF, EPUB and Kindle. Book excerpt: Robust Automatic Speech Recognition: A Bridge to Practical Applications establishes a solid foundation for automatic speech recognition that is robust against acoustic environmental distortion. It provides a thorough overview of classical and modern noise-and reverberation robust techniques that have been developed over the past thirty years, with an emphasis on practical methods that have been proven to be successful and which are likely to be further developed for future applications.The strengths and weaknesses of robustness-enhancing speech recognition techniques are carefully analyzed. The book covers noise-robust techniques designed for acoustic models which are based on both Gaussian mixture models and deep neural networks. In addition, a guide to selecting the best methods for practical applications is provided.The reader will: Gain a unified, deep and systematic understanding of the state-of-the-art technologies for robust speech recognition Learn the links and relationship between alternative technologies for robust speech recognition Be able to use the technology analysis and categorization detailed in the book to guide future technology development Be able to develop new noise-robust methods in the current era of deep learning for acoustic modeling in speech recognition The first book that provides a comprehensive review on noise and reverberation robust speech recognition methods in the era of deep neural networks Connects robust speech recognition techniques to machine learning paradigms with rigorous mathematical treatment Provides elegant and structural ways to categorize and analyze noise-robust speech recognition techniques Written by leading researchers who have been actively working on the subject matter in both industrial and academic organizations for many years