Vorliegende Sprache |
eng |
Hinweise auf parallele Ausgaben |
356087492 Buchausg. u.d.T.: ‡Li, Qi: Speaker authentication |
ISBN |
978-3-642-23730-0 |
Name |
Li, Qi (Peter) |
T I T E L |
Speaker Authentication |
Verlagsort |
Berlin, Heidelberg |
Verlag |
Springer-Verlag Berlin Heidelberg |
Erscheinungsjahr |
2012 |
2012 |
Umfang |
Online-Ressource (XXV, 237p. 83 illus., 19 illus. in color, digital) |
Reihe |
Signals and Communication Technology |
Notiz / Fußnoten |
Includes bibliographical references and index |
Weiterer Inhalt |
Speaker Authentication; Preface; Contents; List of Tables; List of Figures; Introduction; 1.1 Authentication; 1.2 Biometric-Based Authentication; 1.3 Information-Based Authentication; 1.4 Speaker Authentication; 1.4.1 Speaker Recognition; 1.4.2 Verbal Information Verification; 1.5 Historical Perspective and Further Reading; 1.6 Book Organization; References; Multivariate Statistical Analysis and One-PassVector Quantization; 2.1 Multivariate Gaussian Distribution; 2.2 Principal Component Analysis; 2.3 Vector Quantization; 2.4 One-Pass VQ; 2.4.1 The One-Pass VQ Algorithm. 2.4.2 Steps of the One-Pass VQ Algorithm2.4.3 Complexity Analysis; 2.4.4 Codebook Design Examples; 2.4.5 Robustness Analysis; 2.5 Segmental K-Means; 2.6 Conclusions; References; Principal Feature Networks for PatternRecognition; 3.1 Overview of the Design Concept; 3.2 Implementations of Principal Feature Networks; 3.3 Hidden Node Design; 3.3.1 Gaussian Discriminant Node; 3.3.2 Fisher's Node Design; 3.4 Principal Component Hidden Node Design; 3.4.1 Principal Component Discriminant Analysis; 3.5 Relation between PC Node and the OptimalGaussian Classifier. 3.6 Maximum Signal-to-Noise-Ratio (SNR) HiddenNode Design3.7 Determining the Thresholds from DesignSpecifications; 3.8 Simplification of the Hidden Nodes; 3.9 Application 1 - Data Recognition; 3.10 Application 2 - Multispectral Pattern Recognition; 3.11 Conclusions; References; Non-Stationary Pattern Recognition; 4.1 Introduction; 4.2 Gaussian Mixture Models (GMM) for StationaryProcess; 4.2.1 An Illustrative Example; 4.3 Hidden Markov Model (HMM) for Non-StationaryProcess; 4.4 Speech Segmentation; 4.5 Bayesian Decision Theory; 4.6 Statistical Verification; 4.7 Conclusions; References. Robust Endpoint Detection5.1 Introduction; 5.2 A Filter for Endpoint Detection; 5.3 Real-Time Endpoint Detection and EnergyNormalization; 5.3.1 A Filter for Both Beginning- and Ending-Edge Detection; 5.3.2 Decision Diagram; 5.3.3 Real-Time Energy Normalization; 5.3.4 Database Evaluation; 5.4 Conclusions; References; Detection-Based Decoder; 6.1 Introduction; 6.2 Change-Point Detection; 6.3 HMM State Change-Point Detection; 6.4 HMM Search-Space Reduction; 6.4.1 Concept of Search-Space Reduction; 6.4.2 Algorithm Summary and Complexity Analysis; 6.5 Experiments. 6.5.1 An Example of State Change-Point Detection6.5.2 Application to Speaker Verification; 6.6 Conclusions; References; Auditory-Based Time Frequency Transform; 7.1 Introduction; 7.1.1 Observing Problems with the Fourier Transform; 7.1.2 Brief Introduction of the Ear; 7.1.3 Time-Frequency Analyses; 7.2 Definition of the Auditory-Based Transform; 7.3 The Inverse Auditory Transform; 7.4 The Discrete-Time and Fast Transform; 7.5 Experiments and Discussions; 7.5.1 Verifying the Inverse Auditory Transform; 7.5.2 Applications; 7.6 Comparisons to Other Transforms; 7.7 Conclusions; References. Auditory-Based Feature Extraction andRobust Speaker Identification |
Titelhinweis |
Buchausg. u.d.T.: ‡Li, Qi: Speaker authentication |
ISBN |
ISBN 978-3-642-23731-7 |
Klassifikation |
TTBM |
UYS |
TEC008000 |
COM073000 |
*68-02 |
68T10 |
62-01 |
94-02 |
621.3828 |
621.399 |
006.4 |
621.39/94 |
TK5102.9 |
TA1637-1638 |
TK7882.S65 |
Kurzbeschreibung |
This book focuses on use of voice as a biometric measure for personal authentication. In particular, "Speaker Recognition" covers two approaches in speaker authentication: speaker verification (SV) and verbal information verification (VIV). The SV approach attempts to verify a speaker's identity based on his/her voice characteristics while the VIV approach validates a speaker's identity through verification of the content of his/her utterance(s). SV and VIV can be combined for new applications. This is still a new research topic with significant potential applications. The book provides with a broad overview of the recent advances in speaker authentication while giving enough attention to advanced and useful algorithms and techniques. It also provides a step by step introduction to the current state of the speaker authentication technology, from the fundamental concepts to advanced algorithms. We will also present major design methodologies and share our experience in developing real and successful speaker authentication systems. Advanced and useful topics and algorithms are selected with real design examples and evaluation results. Special attention is given to the topics related to improving overall system robustness and performances, such as robust endpoint detection, fast discriminative training theory and algorithms, detection-based decoding, sequential authentication, etc. For example, the sequential authentication was developed based on statistical sequential testing theory. By adding enough subtests, a speaker authentication system can achieve any accuracy requirement. The procedure of designing the sequential authentication will be presented. For any presented technique, we will provide experimental results to validate the usefulness. We will also highlight the important developments in academia, government, and industry, and outline a few open issues. As the methodologies developed in speaker authentication span several diverse fields, the tutorial book provides an introductory forum for a broad spectrum of researchers and developers from different areas to acquire the knowledge and skills to engage in the interdisciplinary fields of user authentication, biometrics, speech and speaker recognition, multimedia, and dynamic pattern recognition |
2. Kurzbeschreibung |
This book focuses on use of voice as a biometric measure for personal authentication. In particular, "Speaker Recognition" covers two approaches in speaker authentication: speaker verification (SV) and verbal information verification (VIV). The SV approach attempts to verify a speaker's identity based on his/her voice characteristics while the VIV approach validates a speaker's identity through verification of the content of his/her utterance(s). SV and VIV can be combined for new applications. This is still a new research topic with significant potential applications. The book provi |
1. Schlagwortkette |
Automatische Sprechererkennung |
Authentifikation |
Merkmalsextraktion |
Biometrie |
Sprachsignal |
Akustische Signalverarbeitung |
Verifikation |
1. Schlagwortkette ANZEIGE DER KETTE |
Automatische Sprechererkennung -- Authentifikation -- Merkmalsextraktion -- Biometrie -- Sprachsignal -- Akustische Signalverarbeitung -- Verifikation |
2. Schlagwortkette |
Automatische Sprechererkennung |
Authentifikation |
Merkmalsextraktion |
Biometrie |
Sprachsignal |
Akustische Signalverarbeitung |
Verifikation |
ANZEIGE DER KETTE |
Automatische Sprechererkennung -- Authentifikation -- Merkmalsextraktion -- Biometrie -- Sprachsignal -- Akustische Signalverarbeitung -- Verifikation |
SWB-Titel-Idn |
355107074 |
Signatur |
Springer E-Book |
Bemerkungen |
Elektronischer Volltext - Campuslizenz |
Elektronische Adresse |
$uhttp://dx.doi.org/10.1007/978-3-642-23731-7 |
Internetseite / Link |
Volltext |
Siehe auch |
Volltext |
Siehe auch |
Inhaltstext |