|
|
Biblioteca Julio Castiñeiras. Sistema de Información Integrado - Facultad de Ingeniería UNLP
Facultad de Ingeniería | 115 esq.47 | Horario: Lunes a Viernes 8 a 19 hs. E-mail: bibcentral@ing.unlp.edu.ar
|
|
|
|
|
|
|
|
|
Información bibliografica (registro INGC-EBK-000552) |
|
|
|
Título: |
Robust Speaker Recognition in Noisy Environments by K. Sreenivasa Rao, Sourjya Sarkar. |
Autor:
|
Rao, K. Sreenivasa.
|
Otros autores: |
|
Sarkar, Sourjya.
|
|
Editado por: |
Springer International Publishing :;Imprint: Springer,
|
Año de publicación: |
2014.
|
Lugar de publicación: |
Cham :
|
Descripción física: |
xii, 139 p. : il. |
ISBN: |
9783319071305
|
Colección: |
SpringerBriefs in Electrical and Computer Engineering,
|
Materias: |
|
Engineering. |
Signal, Image and Speech Processing. |
|
Notas: |
Robust Speaker Verification â_" A Review -- Speaker Verification in Noisy Environments using Gaussian Mixture Models -- Stochastic Feature Compensation for Robust Speaker Verification -- Robust Speaker Modeling for Speaker Verification in Noisy Environments. |
Sumario: |
This book discusses speaker recognition methods to deal with realistic variable noisy environments. The text covers authentication systems for; robust noisy background environments, functions in real time and incorporated in mobile devices. The book focuses on different approaches to enhance the accuracy of speaker recognition in presence of varying background environments. The authors examine: (a) Feature compensation using multiple background models, (b) Feature mapping using data-driven stochastic models, (c) Design of super vector- based GMM-SVM framework for robust speaker recognition, (d) Total variability modeling (i-vectors) in a discriminative framework and (e) Boosting method to fuse evidences from multiple SVM models. |
URL: |
http://dx.doi.org/10.1007/978-3-319-07130-5
|
|
|
Tapa y contenido (Amazon.com) |
|
|
El software empleado por esta biblioteca esta basado en el
Koha
Software OSS para gestion de Bibliotecas, y cumple estándares internacionales de informacion web
Número de visitantes:
|
|
|