ENGLISH

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

By Wolfgang Minker (auth.) , Tobias Herbig , Franz Gerl

Book information

Publisher
Springer-Verlag Berlin Heidelberg
Year
2011
ISBN
978-3-642-19898-4, 978-3-642-19899-1
DOI
10.1007/978-3-642-19899-1
Language
english
Format
PDF
Filesize
3 MB (2625919 bytes)
Series
Signals and Communication Technology
Edition
1
Pages
172\177
Orientation
yes
Scanned
yes
Time added
2013-08-01 04:00:00
Image and Speech Processing; Biometrics; CommunicaNetworks; User Interfaces and Human Computer InterSignal

Description

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.

Similar books