Ebook: Self-Learning Speaker Identification: A System for Enhanced Speech Recognition

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.

---

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.

---

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.


Content:
Front Matter....Pages -
Introduction....Pages 1-4
Fundamentals....Pages 5-57
Combining Self-Learning Speaker Identification and Speech Recognition....Pages 59-70
Combined Speaker Adaptation....Pages 71-82
Unsupervised Speech Controlled System with Long-Term Adaptation....Pages 83-113
Evolution of an Adaptive Unsupervised Speech Controlled System....Pages 115-143
Summary and Conclusion....Pages 145-148
Outlook....Pages 149-152
Back Matter....Pages -

---

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.


Content:
Front Matter....Pages -
Introduction....Pages 1-4
Fundamentals....Pages 5-57
Combining Self-Learning Speaker Identification and Speech Recognition....Pages 59-70
Combined Speaker Adaptation....Pages 71-82
Unsupervised Speech Controlled System with Long-Term Adaptation....Pages 83-113
Evolution of an Adaptive Unsupervised Speech Controlled System....Pages 115-143
Summary and Conclusion....Pages 145-148
Outlook....Pages 149-152
Back Matter....Pages -
....