Voice Modeling Methods : for Automatic Speaker Recognition

Thilo Stadelmann

ISBN 10: 3838116321 / ISBN 13: 9783838116327

Editore: Südwestdeutscher Verlag Für Hochschulschriften AG Co. KG, 2010

Riguardo questo articolo

nach der Bestellung gedruckt Neuware - Printed after ordering - Building a voice model means to capture the characteristics of a speaker's voice in a data structure. This data structure is then used by a computer for further processing, such as comparison with other voices. Voice modeling is a vital step in the process of automatic speaker recognition that itself is the foundation of several applied technologies: (a) biometric authentication, (b) speech recognition and (c) multimedia indexing. Current automatic speaker recognition works well under relatively constrained circumstances, such as studio recordings, or when prior knowledge on the number and identity of occurring speakers is available. Under more adverse conditions, such as in feature films or amateur material on the web, the achieved speaker recognition scores drop below a rate that is acceptable for an end user or for further processing. In this book, algorithmic and methodic improvements to the state of the art in automatic speaker recognition are presented. They are accompanied by a capacious software toolkit called 'sclib'. Additionally, the method of 'Eidetic Design' facilitates intuitive algorithm design, development and teaching.

Codice articolo 9783838116327

Dati bibliografici

• Titolo: Voice Modeling Methods : for Automatic Speaker Recognition
• Editore: Südwestdeutscher Verlag Für Hochschulschriften AG Co. KG
• Data di pubblicazione: 2010
• Lingua: Inglese
• ISBN 10: 3838116321
• ISBN 13: 9783838116327
• Rilegatura: Taschenbuch
• Condizione: Neu
• Dimensioni: 220 L x 150 A x 15 P (millimetri) 220 millimetri di larghezza per 150 millimetri di altezza per 15 millimetri di profondità
• Peso: 375 grammi

Descrizione articolo

Riassunto

Building a voice model means to capture the characteristics of a speaker's voice in a data structure. This data structure is then used by a computer for further processing, such as comparison with other voices. Voice modeling is a vital step in the process of automatic speaker recognition that itself is the foundation of several applied technologies: (a) biometric authentication, (b) speech recognition and (c) multimedia indexing. Current automatic speaker recognition works well under relatively constrained circumstances, such as studio recordings, or when prior knowledge on the number and identity of occurring speakers is available. Under more adverse conditions, such as in feature films or amateur material on the web, the achieved speaker recognition scores drop below a rate that is acceptable for an end user or for further processing. In this book, algorithmic and methodic improvements to the state of the art in automatic speaker recognition are presented. They are accompanied by a capacious software toolkit called "sclib". Additionally, the method of "Eidetic Design" facilitates intuitive algorithm design, development and teaching.

L'autore

Thilo was born in Lemgo/Germany in the 1980's and still loves the music of this time. Maybe this is why he choose to analyze acoustic data in his doctoral studies? When he's not playing music or doing research and development, he's probably exploring some new fun sport together with his wife or thinks about god and his world.