Speech Enhancement Theory and Practice, Second Edition

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 StepsOrganized 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.What’s New in This EditionUpdates in every chapterA new chapter on objective speech intelligibility measuresA new chapter on algorithms for improving speech intelligibilityReal-world noise recordings (on downloadable resources)MATLAB® code for the implementation of intelligibility measures (on downloadable resources)MATLAB and C/C++ code for the implementation of algorithms to improve speech intelligibility (on downloadable resources)Valuable Insights from a Pioneer in Speech EnhancementClear 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 downloadable resources with Code and RecordingsThe downloadable resources provide MATLAB implementations of representative speech enhancement algorithms as well as speech and noise databases for the evaluation of enhancement algorithms.

IntroductionUnderstanding the Enemy: NoiseClasses of Speech Enhancement AlgorithmsBook OrganizationReferencesPart I FundamentalsDiscrete-Time Signal Processing and Short-Time Fourier AnalysisDiscrete-Time SignalsLinear Time-Invariant Discrete-Time Systemsz-TransformDiscrete-Time Fourier TransformShort-Time Fourier TransformSpectrographic Analysis of Speech SignalsSummaryReferencesSpeech Production and PerceptionSpeech SignalSpeech Production ProcessEngineering Model of Speech ProductionClasses of Speech SoundsAcoustic Cues in Speech PerceptionSummaryReferencesNoise Compensation by Human ListenersIntelligibility of Speech in Multiple-Talker ConditionsAcoustic Properties of Speech Contributing to RobustnessPerceptual Strategies for Listening in NoiseSummaryReferencesPart II AlgorithmsSpectral-Subtractive AlgorithmsBasic Principles of Spectral SubtractionGeometric View of Spectral SubtractionShortcomings of the Spectral Subtraction MethodSpectral Subtraction Using OversubtractionNonlinear Spectral SubtractionMultiband Spectral SubtractionMMSE Spectral Subtraction AlgorithmExtended Spectral SubtractionSpectral Subtraction Using Adaptive Gain AveragingSelective Spectral SubtractionSpectral Subtraction Based on Perceptual PropertiesPerformance of Spectral Subtraction AlgorithmsSummaryReferencesWiener FilteringIntroduction to Wiener Filter TheoryWiener Filters in the Time DomainWiener Filters in the Frequency DomainWiener Filters and Linear PredictionWiener Filters for Noise ReductionIterative Wiener FilteringImposing Constraints on Iterative Wiener FilteringConstrained Iterative Wiener FilteringConstrained Wiener FilteringEstimating the Wiener Gain FunctionIncorporating Psychoacoustic Constraints in Wiener FilteringCodebook-Driven Wiener FilteringAudible Noise Suppression AlgorithmSummaryReferencesStatistical-Model-Based MethodsMaximum-Likelihood EstimatorsBayesian EstimatorsMMSE EstimatorImprovements to the Decision-Directed ApproachImplementation and Evaluation of the MMSE EstimatorElimination of Musical NoiseLog-MMSE EstimatorMMSE Estimation of the pth-Power SpectrumMMSE Estimators Based on Non-Gaussian DistributionsMaximum A Posteriori (Map) EstimatorsGeneral Bayesian EstimatorsPerceptually Motivated Bayesian EstimatorsIncorporating Speech Absence Probability in Speech EnhancementMethods for Estimating the A Priori Probability of Speech AbsenceSummaryReferencesSubspace AlgorithmsIntroductionUsing SVD for Noise Reduction: TheorySVD-Based Algorithms: White NoiseSVD-Based Algorithms: Colored NoiseSVD-Based Methods: A Unified ViewEVD-Based Methods: White NoiseEVD-Based Methods: Colored NoiseEVD-Based Methods: A Unified ViewPerceptually Motivated Subspace AlgorithmsSubspace-Tracking AlgorithmsSummaryReferencesNoise-Estimation AlgorithmsVoice Activity Detection vs. Noise EstimationIntroduction to Noise-Estimation AlgorithmsMinimal-Tracking AlgorithmsTime-Recursive Averaging Algorithms for Noise EstimationHistogram-Based TechniquesOther Noise-Estimation AlgorithmsObjective Comparison of Noise-Estimation AlgorithmsSummaryReferencesPart III EvaluationEvaluating Performance of Speech Enhancement AlgorithmsQuality vs. IntelligibilityEvaluating Intelligibility of Processed SpeechEvaluating Quality of Processed SpeechEvaluating Reliability of Quality Judgments: Recommended PracticeSummaryReferencesObjective Quality and Intelligibility MeasuresObjective Quality MeasuresEvaluation of Objective Quality MeasuresQuality Measures: Summary of Findings and Future DirectionsSpeech Intelligibility MeasuresEvaluation of Intelligibility MeasuresIntelligibility Measures: Summary of Findings and Future DirectionsSummaryReferencesComparison of Speech Enhancement AlgorithmsNOIZEUS: A Noisy Speech Corpus for Quality Evaluation of Speech Enhancement AlgorithmsComparison of Enhancement Algorithms: Speech QualityComparison of Enhancement Algorithms: Speech IntelligibilitySummaryReferencesPart IV Future StepsAlgorithms That Can Improve Speech IntelligibilityReasons for the Absence of Intelligibility Improvement with Existing Noise-Reduction AlgorithmsAlgorithms Based on Channel Selection: A Different Paradigm for Noise ReductionChannel-Selection CriteriaIntelligibility Evaluation of Channel-Selection-Based Algorithms: Ideal ConditionsImplementation of Channel-Selection-Based Algorithms in Realistic ConditionsEvaluating Binary Mask Estimation AlgorithmsChannel Selection and Auditory Scene AnalysisSummaryReferencesAppendicesAppendix A: Special Functions and IntegralsAppendix B: Derivation of the MMSE EstimatorAppendix C: MATLAB® Code and Speech/Noise DatabasesIndex

Philipos C. Loizou earned his bachelor’s, master’s, and doctorate degrees in electrical engineering from Arizona State University in Tempe. A pioneer in the field of speech enhancement and noise reduction in cochlear implants, Dr. Loizou was one of the first to develop specific enhancement algorithms that directly improve intelligibility. He was a postdoctoral fellow in the Department of Speech and Hearing Science at Arizona State University, an assistant professor at the University of Arkansas in Little Rock, and Cecil and Ida Green Professor in the Department of Electrical Engineering at the University of Texas at Dallas. Dr. Loizou was a fellow of the Acoustical Society of America. He was an associate editor of the International Journal of Audiology (2010–2012), IEEE Transactions on Biomedical Engineering (2009–2011), IEEE Transactions on Speech and Audio Processing (1999–2002), and IEEE Signal Processing Letters (2006–2009) and a member of the Speech Technical Committee (2008–2010) of the IEEE Signal Processing Society. He authored or coauthored numerous publications, including three textbooks. For more information, see Dr. Loizou’s profile at the University of Texas at Dallas. Watch a video of Dr. Loizou talking about technology that would allow cochlear implant users to easily adjust settings on their hearing devices through a smartphone.