Robustness-related issues in speaker recognition
Zheng, Thomas Fang,
Robustness-related issues in speaker recognition Thomas Fang Zheng, Lantian Li. - 1 recurso en línea ilustraciones - SpringerBriefs in Electrical and Computer Engineering. Signal Processing .
SpringerLink
Incluye referencias bibliográficas
Preface; Acknowledgements; Contents; 1 Speaker Recognition: Introduction; 1.1 Basic Concepts; 1.2 Development History; 1.3 System Framework; 1.4 Categories; 1.4.1 Identification, Verification, Detection, and Tracking; 1.4.2 Text-Dependent, Text-Independent and Text-Prompted; 1.5 Performance Evaluations; 1.5.1 Evaluation Metrics for Verification or Open-Set Identification; 1.5.2 Evaluation Metrics for Close-Set Identification; References; 2 Environment-Related Robustness Issues; 2.1 Background Noise; 2.1.1 Speech Enhancement; 2.1.2 Feature Compensation; 2.1.3 Robust Modeling. 2.1.4 Score Normalization2.2 Channel Mismatch; 2.2.1 Feature Transformation; 2.2.2 Channel Compensation; 2.2.3 Score Normalization; 2.3 Multiple Speakers; 2.3.1 Robust Features; 2.3.2 Robust Speaker Models; 2.3.3 Segmentation and Clustering Algorithms; 2.4 Discussions; References; 3 Speaker-Related Robustness Issues; 3.1 Genders; 3.2 Physical Conditions; 3.3 Speaking Styles; 3.3.1 Emotion; 3.3.2 Speaking Rate; 3.3.3 Idiom; 3.4 Cross Languages; 3.5 Time Varying; 3.6 Discussion; References; 4 Application-Oriented Robustness Issues; 4.1 Application Scenarios; 4.1.1 User Authentication. 4.1.2 Public Security and Judicature4.1.3 Speaker Adaptation in Speech Recognition; 4.1.4 Multi-speaker Environments; 4.1.5 Personalization; 4.2 Short Utterance; 4.3 Anti-spoofing; 4.3.1 Impersonation; 4.3.2 Speech Synthesis; 4.3.3 Voice Conversion; 4.3.4 Replay; 4.3.5 Voice Liveness Detection; 4.4 Cross Encoding Schemes; 4.5 Discussion; References; 5 Conclusions and Future Work.
This book presents an overview of speaker recognition technologies with an emphasis on dealing with robustness issues. Firstly, the book gives an overview of speaker recognition, such as the basic system framework, categories under different criteria, performance evaluation and its development history. Secondly, with regard to robustness issues, the book presents three categories, including environment-related issues, speaker-related issues and application-oriented issues. For each category, the book describes the current hot topics, existing technologies, and potential research focuses in the future. The book is a useful reference book and self-learning guide for early researchers working in the field of robust speech recognition.
9789811032387 9811032386
Identificación de personas
TK7895.S65 / Z446 2017 EB
Robustness-related issues in speaker recognition Thomas Fang Zheng, Lantian Li. - 1 recurso en línea ilustraciones - SpringerBriefs in Electrical and Computer Engineering. Signal Processing .
SpringerLink
Incluye referencias bibliográficas
Preface; Acknowledgements; Contents; 1 Speaker Recognition: Introduction; 1.1 Basic Concepts; 1.2 Development History; 1.3 System Framework; 1.4 Categories; 1.4.1 Identification, Verification, Detection, and Tracking; 1.4.2 Text-Dependent, Text-Independent and Text-Prompted; 1.5 Performance Evaluations; 1.5.1 Evaluation Metrics for Verification or Open-Set Identification; 1.5.2 Evaluation Metrics for Close-Set Identification; References; 2 Environment-Related Robustness Issues; 2.1 Background Noise; 2.1.1 Speech Enhancement; 2.1.2 Feature Compensation; 2.1.3 Robust Modeling. 2.1.4 Score Normalization2.2 Channel Mismatch; 2.2.1 Feature Transformation; 2.2.2 Channel Compensation; 2.2.3 Score Normalization; 2.3 Multiple Speakers; 2.3.1 Robust Features; 2.3.2 Robust Speaker Models; 2.3.3 Segmentation and Clustering Algorithms; 2.4 Discussions; References; 3 Speaker-Related Robustness Issues; 3.1 Genders; 3.2 Physical Conditions; 3.3 Speaking Styles; 3.3.1 Emotion; 3.3.2 Speaking Rate; 3.3.3 Idiom; 3.4 Cross Languages; 3.5 Time Varying; 3.6 Discussion; References; 4 Application-Oriented Robustness Issues; 4.1 Application Scenarios; 4.1.1 User Authentication. 4.1.2 Public Security and Judicature4.1.3 Speaker Adaptation in Speech Recognition; 4.1.4 Multi-speaker Environments; 4.1.5 Personalization; 4.2 Short Utterance; 4.3 Anti-spoofing; 4.3.1 Impersonation; 4.3.2 Speech Synthesis; 4.3.3 Voice Conversion; 4.3.4 Replay; 4.3.5 Voice Liveness Detection; 4.4 Cross Encoding Schemes; 4.5 Discussion; References; 5 Conclusions and Future Work.
This book presents an overview of speaker recognition technologies with an emphasis on dealing with robustness issues. Firstly, the book gives an overview of speaker recognition, such as the basic system framework, categories under different criteria, performance evaluation and its development history. Secondly, with regard to robustness issues, the book presents three categories, including environment-related issues, speaker-related issues and application-oriented issues. For each category, the book describes the current hot topics, existing technologies, and potential research focuses in the future. The book is a useful reference book and self-learning guide for early researchers working in the field of robust speech recognition.
9789811032387 9811032386
Identificación de personas
TK7895.S65 / Z446 2017 EB