000			02342nam a2200361za04500
001			17610
008			050703s2011 gw eng d
020			_a9783642198991 99783642198991
082			_a621.382 _b223
100			_aHerbig, Tobias. _eauthor. _935763
245			_aSelf-Learning Speaker Identification _h[electronic resource]: _bA System for Enhanced Speech Recognition / _cby Tobias Herbig, Franz Gerl, Wolfgang Minker.
300			_aXII, 172 p. _bonline resource.
490			_aSignals and Communication Technology
490			_x-1860-4862
505			_aIntroduction -- State of the Art -- Fundamentals -- Speech Production -- Front-End -- Speaker Change -- Speaker Identification.-Speaker Adaptation.
520			_aCurrent 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.
650			_aEngineering. _996
650			_aEngineering. _996
650			_aUser Interfaces and Human Computer Interaction. _930657
650			_935764 _aBIOMETRICS
650			_935764 _aBIOMETRICS
650			_933860 _aSIGNAL, IMAGE AND SPEECH PROCESSING
650			_933627 _aCOMMUNICATIONS ENGINEERING, NETWORKS
650			_930656 _aTELECOMUNICACIÓN
650			_923206 _aCOMPUTER SCIENCE
700			_aGerl, Franz. _935765
700			_eauthor. _935766
700			_aMinker, Wolfgang. _934009
700			_eauthor. _935766
710			_aSpringerLink (Online service) _9111
856			_uhttp://springer.escuelaing.metaproxy.org/book/10.1007/978-3-642-19899-1 _yir a documento _qURL
942			_2ddc _cCF
999			_c14235 _d14235