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 ov...

Szczegółowa specyfikacja

Zapisane w:
Opis bibliograficzny
Główni autorzy: Herbig, Tobias, 19..-, Minker, Wolfgang, 1967- (Autor)
Format: Livre numérique
Język:Anglais
Wydane: Berlin, Heidelberg : Springer Berlin Heidelberg 2011.
Cham : Springer Nature
Seria:Signals and Communication Technology
Dostęp online:Accès sur la plateforme de l'éditeur
Accès sur la plateforme Istex
Accès Université d'Orléans
Accès INSA CVL
Komentarz: Archives Springer e-books (Licence nationale)
Archives Springer e-books (Licence nationale)
Autres localisations: Voir dans le Sudoc
Edition sous un autre format:• Self-Learning Speaker Identification, Texte imprimé, 9783642198984
• Self-Learning Speaker Identification, Texte imprimé, 9783642199004
• Self-Learning Speaker Identification, Texte imprimé, 9783642268809
LEADER 03069nam a22003497a 4500
001 973459
008 111115s2011 xx ||| |||| 00| 0 eng d
009 PPN156313782
020 |a 9783642198991 
041 0 |a eng 
082 |a 621.382 
100 1 |a Herbig, Tobias,  |d 19..- 
245 1 0 |a Self-learning speaker identification :  |b a system for enhanced speech recognition   |c by Tobias Herbig, Franz Gerl, Wolfgang Minker. 
260 |a Berlin, Heidelberg :  |b Springer Berlin Heidelberg. 
260 |a Cham :  |b Springer Nature,  |c 2011. 
490 0 |a Signals and Communication Technology  |x 1860-4870 
500 |a Archives Springer e-books (Licence nationale) 
500 |a Archives Springer e-books (Licence nationale) 
505 0 |a Introduction -- State of the Art -- Fundamentals -- Speech Production -- Front-End -- Speaker Change -- Speaker Identification.-Speaker Adaptation. 
506 |a Accès en ligne pour les établissements français bénéficiaires des licences nationales 
506 |a Accès soumis à abonnement pour tout autre établissement 
506 |a Conditions particulières de réutilisation pour les bénéficiaires des licences nationales. chttps://www.licencesnationales.fr/springer-nature-ebooks-contrat-licence-ln-2017 
520 |a 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. 
700 1 |a Minker, Wolfgang,  |d 1967-  |4 aut 
776 0 |t Self-Learning Speaker Identification  |b Texte imprimé  |z 9783642198984 
776 0 |t Self-Learning Speaker Identification  |b Texte imprimé  |z 9783642199004 
776 0 |t Self-Learning Speaker Identification  |b Texte imprimé  |z 9783642268809 
856 4 |q PDF  |u https://doi.org/10.1007/978-3-642-19899-1  |z Accès sur la plateforme de l'éditeur 
856 4 |u https://revue-sommaire.istex.fr/ark:/67375/8Q1-37BR2K8Z-3  |z Accès sur la plateforme Istex 
856 4 |5 452349901:750612347  |u https://ezproxy.univ-orleans.fr/login?url=https://doi.org/10.1007/978-3-642-19899-1  |z Accès Université d'Orléans 
856 4 |5 180339901:753971380  |u https://ezproxy.insa-cvl.fr/login?qurl=https://doi.org/10.1007/978-3-642-19899-1  |z Accès INSA CVL 
997 |0 973459  |1 Livre numérique  |a Ressource numérique  |b INSA  |b ENSA  |c 0/Bibliothèque numérique/  |c 1/Bibliothèque numérique/Autre ressource numérique/