Audio Source Separation and Speech Enhancement.

Intro -- Table of Contents -- List of Authors -- Preface -- Acknowledgment -- Notations -- Acronyms -- About the Companion Website -- Part I: Prerequisites -- Chapter 1: Introduction -- 1.1 Why are Source Separation and Speech Enhancement Needed? -- 1.2 What are the Goals of Source Separation and Speech Enhancement? -- 1.3 How can Source Separation and Speech Enhancement be Addressed? -- 1.4 Outline -- Bibliography -- Chapter 2: Time‐Frequency Processing: Spectral Properties -- 2.1 Time‐Frequency Analysis and Synthesis -- 2.2 Source Properties in the Time‐Frequency Domain -- 2.3 Filtering in the Time‐Frequency Domain -- 2.4 Summary -- Bibliography -- Chapter 3: Acoustics: Spatial Properties -- 3.1 Formalization of the Mixing Process -- 3.2 Microphone Recordings -- 3.3 Artificial Mixtures -- 3.4 Impulse Response Models -- 3.5 Summary -- Bibliography -- Chapter 4: Multichannel Source Activity Detection, Localization, and Tracking -- 4.1 Basic Notions in Multichannel Spatial Audio -- 4.2 Multi‐Microphone Source Activity Detection -- 4.3 Source Localization -- 4.4 Summary -- Bibliography -- Part II: Single‐Channel Separation and Enhancement -- Chapter 5: Spectral Masking and Filtering -- 5.1 Time‐Frequency Masking -- 5.2 Mask Estimation Given the Signal Statistics -- 5.3 Perceptual Improvements -- 5.4 Summary -- Bibliography -- Chapter 6: Single‐Channel Speech Presence Probability Estimation and Noise Tracking -- 6.1 Speech Presence Probability and its Estimation -- 6.2 Noise Power Spectrum Tracking -- 6.3 Evaluation Measures -- 6.4 Summary -- Bibliography -- Chapter 7: Single‐Channel Classification and Clustering Approaches -- 7.1 Source Separation by Computational Auditory Scene Analysis -- 7.2 Source Separation by Factorial HMMs -- 7.3 Separation Based Training -- 7.4 Summary -- Bibliography -- Chapter 8: Nonnegative Matrix Factorization.

8.1 NMF and Source Separation -- 8.2 NMF Theory and Algorithms -- 8.3 NMF Dictionary Learning Methods -- 8.4 Advanced NMF Models -- 8.5 Summary -- Bibliography -- Chapter 9: Temporal Extensions of Nonnegative Matrix Factorization -- 9.1 Convolutive NMF -- 9.2 Overview of Dynamical Models -- 9.3 Smooth NMF -- 9.4 Nonnegative State‐Space Models -- 9.5 Discrete Dynamical Models -- 9.6 The Use of Dynamic Models in Source Separation -- 9.7 Which Model to Use? -- 9.8 Summary -- 9.9 Standard Distributions -- Bibliography -- Part III: Multichannel Separation and Enhancement -- Chapter 10: Spatial Filtering -- 10.1 Fundamentals of Array Processing -- 10.2 Array Topologies -- 10.3 Data‐Independent Beamforming -- 10.4 Data‐Dependent Spatial Filters: Design Criteria -- 10.5 Generalized Sidelobe Canceler Implementation -- 10.6 Postfilters -- 10.7 Summary -- Bibliography -- Chapter 11: Multichannel Parameter Estimation -- 11.1 Multichannel Speech Presence Probability Estimators -- 11.2 Covariance Matrix Estimators Exploiting SPP -- 11.3 Methods for Weakly Guided and Strongly Guided RTF Estimation -- 11.4 Summary -- Bibliography -- Chapter 12: Multichannel Clustering and Classification Approaches -- 12.1 Two‐Channel Clustering -- 12.2 Multichannel Clustering -- 12.3 Multichannel Classification -- 12.4 Spatial Filtering Based on Masks -- 12.5 Summary -- Bibliography -- Chapter 13: Independent Component and Vector Analysis -- 13.1 Convolutive Mixtures and their Time‐Frequency Representations -- 13.2 Frequency‐Domain Independent Component Analysis -- 13.3 Independent Vector Analysis -- 13.4 Example -- 13.5 Summary -- Bibliography -- Chapter 14: Gaussian Model Based Multichannel Separation -- 14.1 Gaussian Modeling -- 14.2 Library of Spectral and Spatial Models -- 14.3 Parameter Estimation Criteria and Algorithms -- 14.4 Detailed Presentation of Some Methods.

14.5 Summary -- Acknowledgment -- Bibliography -- Chapter 15: Dereverberation -- 15.1 Introduction to Dereverberation -- 15.2 Reverberation Cancellation Approaches -- 15.3 Reverberation Suppression Approaches -- 15.4 Direct Estimation -- 15.5 Evaluation of Dereverberation -- 15.6 Summary -- Bibliography -- Part IV: Application Scenarios and Perspectives -- Chapter 16: Applying Source Separation to Music -- 16.1 Challenges and Opportunities -- 16.2 Nonnegative Matrix Factorization in the Case of Music -- 16.3 Taking Advantage of the Harmonic Structure of Music -- 16.4 Nonparametric Local Models: Taking Advantage of Redundancies in Music -- 16.5 Taking Advantage of Multiple Instances -- 16.6 Interactive Source Separation -- 16.7 Crowd‐Based Evaluation -- 16.8 Some Examples of Applications -- 16.9 Summary -- Bibliography -- Chapter 17: Application of Source Separation to Robust Speech Analysis and Recognition -- 17.1 Challenges and Opportunities -- 17.2 Applications -- 17.3 Robust Speech Analysis and Recognition -- 17.4 Integration of Front‐End and Back‐End -- 17.5 Use of Multimodal Information with Source Separation -- 17.6 Summary -- Bibliography -- Chapter 18: Binaural Speech Processing with Application to Hearing Devices -- 18.1 Introduction to Binaural Processing -- 18.2 Binaural Hearing -- 18.3 Binaural Noise Reduction Paradigms -- 18.4 The Binaural Noise Reduction Problem -- 18.5 Extensions for Diffuse Noise -- 18.6 Extensions for Interfering Sources -- 18.7 Summary -- Bibliography -- Chapter 19: Perspectives -- 19.1 Advancing Deep Learning -- 19.2 Exploiting Phase Relationships -- 19.3 Advancing Multichannel Processing -- 19.4 Addressing Multiple‐Device Scenarios -- 19.5 Towards Widespread Commercial Use -- Acknowledgment -- Bibliography -- Index -- End User License Agreement.

Description based on publisher supplied metadata and other sources.

Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2024. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.