Vorliegende Sprache |
eng |
Hinweise auf parallele Ausgaben |
347379478 Buchausg. u.d.T.: ‡Herbig, Tobias, 1979 - : Self-learning speaker identification |
ISBN |
978-3-642-19898-4 |
Name |
Herbig, Tobias |
Gerl, Franz |
Name ANZEIGE DER KETTE |
Gerl, Franz |
Name |
Minker, Wolfgang |
T I T E L |
Self-Learning Speaker Identification |
Zusatz zum Titel |
A System for Enhanced Speech Recognition |
Verlagsort |
Berlin, Heidelberg |
Verlag |
Springer-Verlag Berlin Heidelberg |
Erscheinungsjahr |
2011 |
2011 |
Umfang |
Online-Ressource (XII, 172p. 51 illus, digital) |
Reihe |
Signals and Communication Technology |
Notiz / Fußnoten |
Includes bibliographical references and index |
Weiterer Inhalt |
Title Page; Self-Learning Speaker Identification for Enhanced Speech Recognition; Contents; Nomenclature; Introduction; Motivation; Overview; Fundamentals; Speech Production; Front-End; Speaker Change Detection; Speaker Identification; Speech Recognition; Speaker Adaptation; Feature Vector Normalization and Enhancement; Summary; Combining Self-Learning Speaker Identification and Speech Recognition; Audio Signal Segmentation; Multi-Stage Speaker Identification and Speech Recognition; Phoneme Based Speaker Identification; First Conclusion; Combined Speaker Adaptation; Motivation; Algorithm. EvaluationSummary; Unsupervised Speech Controlled System with Long-Term Adaptation; Motivation; Joint Speaker Identification and Speech Recognition; Reference Implementation; Evaluation; Summary and Discussion; Evolution of an Adaptive Unsupervised Speech Controlled System; Motivation; Posterior Probability Depending on the Training Level; Closed-Set Speaker Tracking; Open-Set Speaker Tracking; System Architecture; Evaluation; Summary; Summary and Conclusion; Outlook; Appendix; References; Index; |
Titelhinweis |
Buchausg. u.d.T.: ‡Herbig, Tobias, 1979 - : Self-learning speaker identification |
ISBN |
ISBN 978-3-642-19899-1 |
Klassifikation |
TTBM |
UYS |
TEC008000 |
COM073000 |
621.382 |
006.454 |
TK5102.9 |
TA1637-1638 |
TK7882.S65 |
Kurzbeschreibung |
Wolfgang Minker |
2. Kurzbeschreibung |
Current speech recognition systems are based on speaker independent speech models and suffer from inter-speaker variations in speech signal characteristics. This work develops an integrated approach for speech and speaker recognition in order to gain space for self-learning opportunities of the system. This work introduces a reliable speaker identification which enables the speech recognizer to create robust speaker dependent models In addition, this book gives a new approach to solve the reverse problem, how to improve speech recognition if speakers can be recognized. The speaker identificati |
1. Schlagwortkette |
Automatische Sprechererkennung |
Sprecheradaption |
Automatische Identifikation |
1. Schlagwortkette ANZEIGE DER KETTE |
Automatische Sprechererkennung -- Sprecheradaption -- Automatische Identifikation |
2. Schlagwortkette |
Automatische Sprechererkennung |
Sprecheradaption |
Automatische Identifikation |
ANZEIGE DER KETTE |
Automatische Sprechererkennung -- Sprecheradaption -- Automatische Identifikation |
SWB-Titel-Idn |
348700105 |
Signatur |
Springer E-Book |
Bemerkungen |
Elektronischer Volltext - Campuslizenz |
Elektronische Adresse |
$uhttp://dx.doi.org/10.1007/978-3-642-19899-1 |
Internetseite / Link |
Volltext |
Siehe auch |
Volltext |