Advertisement

Self-Learning Speaker Identification

A System for Enhanced Speech Recognition

  • Tobias Herbig
  • Franz Gerl
  • Wolfgang Minker

Part of the Signals and Communication Technology book series (SCT)

Table of contents

  1. Front Matter
  2. Tobias Herbig, Franz Gerl, Wolfgang Minker
    Pages 1-4
  3. Tobias Herbig, Franz Gerl, Wolfgang Minker
    Pages 5-57
  4. Tobias Herbig, Franz Gerl, Wolfgang Minker
    Pages 59-70
  5. Tobias Herbig, Franz Gerl, Wolfgang Minker
    Pages 71-82
  6. Tobias Herbig, Franz Gerl, Wolfgang Minker
    Pages 83-113
  7. Tobias Herbig, Franz Gerl, Wolfgang Minker
    Pages 115-143
  8. Tobias Herbig, Franz Gerl, Wolfgang Minker
    Pages 145-148
  9. Tobias Herbig, Franz Gerl, Wolfgang Minker
    Pages 149-152
  10. Back Matter

About this book

Introduction


Current speech recognition systems suffer from variation of voice
characteristics between speakers as they are usually based on speaker
independent speech models. In order to resolve this issue, adaptation
methods have been developed in many state-of-the-art systems. However,
information acquired over time is still lost whenever another speaker intermittently
uses the recognition system. This work therefore develops an integrated
approach for speech and speaker recognition in order to improve the
self-learning opportunities of the system. A speaker adaptation scheme
is introduced. It is suited for fast short-term and detailed long-term
adaptation. These adaptation profiles are then used for an efficient
speaker recognition system. The speaker identification enables the
speaker adaptation to track different speakers which results in an
optimal long-term adaptation.

Keywords

Speaker Authenicationj Speaker Indentification Speaker recognition Speech recognition

Authors and affiliations

  • Tobias Herbig
    • 1
  • Franz Gerl
    • 2
  • Wolfgang Minker
    • 1
  1. 1.Institute of Information TechnologyUniversity of UlmUlmGermany
  2. 2.Dept. Speech RecognitionHarman Becker Automotive Systems GmbHUlmGermany

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-642-19899-1
  • Copyright Information Springer-Verlag Berlin Heidelberg 2011
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Engineering
  • Print ISBN 978-3-642-19898-4
  • Online ISBN 978-3-642-19899-1
  • Series Print ISSN 1860-4862
  • Buy this book on publisher's site