| Description |
1 online resource (x, 422 pages) |
| Contents |
Introduction to sound scene and event analysis. -- The Machine Learning Approach for Analysis of Sound Scenes and Events -- Acoustics and psychacoustics of sound scenes and events -- Acoustic features for environmental sound analysis -- Statistical Methods for Scene and Event Classification -- Datasets and evaluation -- Everyday Sound Categorization -- Approaches to complex sound scene analysis -- Multiview approaches to event detection and scene analysis -- Sound sharing and retrieval -- Computational bioacoustic scene analysis -- Audio Event Recognition in the Smart Home -- Sound Analysis in Smart Cities -- Future Perspective -- Index |
|
Preface; Contents; Contributors; Part I Foundations; 1 Introduction to Sound Scene and Event Analysis; 1.1 Motivation; 1.2 What is Computational Analysis of Sound Scenes and Events?; 1.3 Related Fields; 1.4 Scientific and Technical Challenges in Computational Analysis of Sound Scenes and Events; 1.5 About This Book; References; 2 The Machine Learning Approach for Analysis of Sound Scenes and Events; 2.1 Introduction; 2.2 Analysis Systems Overview; 2.3 Data Acquisition; 2.3.1 Source Audio; 2.3.2 Reference Annotations; 2.4 Audio Processing; 2.4.1 Pre-processing; 2.4.2 Feature Extraction |
|
2.5 Supervised Learning and Recognition2.5.1 Learning; 2.5.2 Generalization; 2.5.3 Recognition; 2.6 An Example Approach Based on Neural Networks; 2.6.1 Sound Classification; 2.6.2 Sound Event Detection; 2.7 Development Process of Audio Analysis Systems; 2.7.1 Technological Research; 2.7.2 Product Demonstrations; 2.7.3 Development Process; 2.8 Conclusions; References; 3 Acoustics and Psychoacoustics of Sound Scenes and Events; 3.1 Introduction ; 3.2 Acoustic and Psychoacoustic Characteristics of Auditory Scenes and Events; 3.2.1 Acoustic Characteristics of Sound Scenes and Events |
|
3.2.1.1 Periodic and Non-periodic Signals3.2.1.2 Sound Production and Propagation; 3.2.2 Psychoacoustics of Auditory Scenes and Events; 3.2.2.1 Models of Peripheral Auditory Processing; 3.2.2.2 Pitch and Loudness; 3.2.2.3 The Dimensional Approach to Timbre; 3.3 The Perception of Auditory Scenes; 3.3.1 Multidimensional Representation; 3.3.2 Temporal Coherence; 3.3.3 Other Effects in Segregation; 3.4 The Perception of Sound Events; 3.4.1 Perception of the Properties of Sound Events: Psychomechanics; 3.4.1.1 Material; 3.4.1.2 Shape and Size; 3.4.1.3 Parameters of Actions |
|
3.4.2 Minimal and Sparse Features for Sound Recognition3.4.2.1 Spectral Regions, Minimal Durations, and Spectro-Temporal Modulations; 3.4.2.2 Sparse Features; 3.4.3 Discussion: On the Dimensionality of Auditory Representations; 3.5 Summary; References; Part II Core Methods; 4 Acoustic Features for Environmental Sound Analysis; 4.1 Introduction; 4.2 Signal Representations; 4.2.1 Signal Acquisition and Preprocessing; 4.2.2 General Time-Frequency Representations; 4.2.3 Log-Frequency and Perceptually Motivated Representations; 4.2.4 Multiscale Representations; 4.2.5 Discussion |
|
4.3 Feature Engineering4.3.1 Temporal Features; 4.3.2 Spectral Shape Features; 4.3.3 Cepstral Features; 4.3.4 Perceptually Motivated Features; 4.3.5 Spectrogram Image-Based Features; 4.3.6 Discussion; 4.4 Feature Learning; 4.4.1 Deep Learning for Feature Extraction; 4.4.2 Matrix Factorisation Techniques; 4.4.3 Discussion; 4.5 Dimensionality Reduction and Feature Selection; 4.5.1 Dimensionality Reduction; 4.5.2 Feature Selection Paradigms; 4.5.3 Filter Approaches; 4.5.4 Embedded Feature Selection; 4.5.4.1 Feature Selection by Sparsity-Inducing Norms; 4.5.4.2 Multiple Kernel Learning |
| Summary |
This book presents computational methods for extracting the useful information from audio signals, collecting the state of the art in the field of sound event and scene analysis. The authors cover the entire procedure for developing such methods, ranging from data acquisition and labeling, through the design of taxonomies used in the systems, to signal processing methods for feature extraction and machine learning methods for sound recognition. The book also covers advanced techniques for dealing with environmental variation and multiple overlapping sound sources, and taking advantage of multiple microphones or other modalities. The book gives examples of usage scenarios in large media databases, acoustic monitoring, bioacoustics, and context-aware devices. Graphical illustrations of sound signals and their spectrographic representations are presented, as well as block diagrams and pseudocode of algorithms. Gives an overview of methods for computational analysis of sounds scenes and events, allowing those new to the field to become fully informed; Covers all the aspects of the machine learning approach to computational analysis of sound scenes and events, ranging from data capture and labeling process to development of algorithms; Includes descriptions of algorithms accompanied by a website from which software implementations can be downloaded, facilitating practical interaction with the techniques |
| Notes |
Includes index |
| Bibliography |
Includes bibliographical references and index |
| Notes |
Print version record |
| In |
Springer eBooks |
| Subject |
Signal processing -- Digital techniques.
|
|
Machine learning.
|
|
Acoustic & sound engineering.
|
|
Society & social sciences.
|
|
User interface design & usability.
|
|
Imaging systems & technology.
|
|
TECHNOLOGY & ENGINEERING -- Mechanical.
|
|
Machine learning
|
|
Signal processing -- Digital techniques
|
| Form |
Electronic book
|
| Author |
Virtanen, Tuomas, editor
|
|
Plumbley, Mark D., editor
|
|
Ellis, Daniel P. W. (Daniel Patrick Whittlesey), editor.
|
| ISBN |
9783319634500 |
|
331963450X |
|
