Над 4 милиона заглавия на английски и други езици! Открийте новата си история още днес! Безплатна доставка за поръчки над 69.99€

Проверка на състоянието на поръчката

Станете част от общност от любители на книгите от цял свят и получавате много предимства. Създай на безплатен акаунт

Безплатна доставка със Еконт над 69.99 €

Куриер Speedy 3.49 € Пункт на Speedy 3.49 € ЕКОНТ 3.99 € Еконтомат/Офис на Еконт 3.99 € Ekont Box 3.99 € Sameday 3.99 € Sameday box 3.99 € Box Now 3.99 €

Контакт

Как се пазарува?

Помощ

Моят акаунт

▸ Празна :-(

Discriminative Classifiers for Speaker Recognition

Name: Discriminative Classifiers for Speaker Recognition
Brand: Südwestdeutscher Verlag für Hochschulschriften
SKU: 06983516
Price: 65.52 EUR
Availability: InStock
Author: Marcel Katz
ISBN: 9783838101910

Marcel Katz

Език

Немски език

Книга С меки корици

Код Либристо: 06983516

Издателство Südwestdeutscher Verlag für Hochschulschriften, ноември 2008

Due to the growing need for security applications,§speaker recognition as the biometric task of§auth... Цялото описание

Код Либристо: 06983516

160 b

65.52 €

128.15 лв

Външен склад Изпращаме след 5-8 дни

До 30 дни за връщане на стоки

Клиентите са закупили също

The Denizen Of Baku: a billion manats love! (reprint edition) Nitesh Singh

С меки корици

9.35 € 18.28 лв

Efeito de um exercício de estabilizaç?o específico versus um exercício convencional para as costas Sucheta Golhar

С меки корици

27.28 € 53.36 лв

Het Keltische Geitendorp David Dom

С меки корици

8.01 € 15.67 лв

Supplement A La Notice Biographique de B.-G. Sage Sage-B-G

С меки корици

13.00 € 25.42 лв

The Helper Catherine Marshall

Аудио компактдиск

27.08 € 52.96 лв

Finding Light Lisa Survillas

С меки корици

13.00 € 25.42 лв

Music and Keyboard in the Classroom Michael Griffin

С меки корици

13.82 € 27.03 лв

Mr Stink David Walliams

С твърди корици

15.00 € 29.34 лв

Linguistic Legitimacy and Social Justice Timothy Reagan

С твърди корици

100.06 € 195.69 лв

Kyouiku Kanji: Japanese Kanji by Grade Level Melissa Rose Lawrence

С меки корици

10.27 € 20.09 лв

Number Tracing With Animals: Learn the Numbers - Number and Counting Practice Workbook for Children in Preschool and Kindergarten - Lavender-Peach Dr Ashley Thomas

С меки корици

7.60 € 14.87 лв

Creature Discomforts Ted Tayler

MP3

17.98 € 35.17 лв

Des Maladies Du Placenta Et Des Membranes (1869) Louis Arthur Alphonse Charpentier

С меки корици

24.87 € 48.64 лв

Sonny Clark Trio: Sonny Clark Trio / Red 180G Sonny Clark Trio

Аудио плоча

19.78 € 38.69 лв

CMFT Corey Taylor

Аудио компактдиск

17.31 € 33.86 лв

ORION CONCERT BAND/HARMONIE JAN VAN DER ROOST Книга

binding.

32.42 € 63.41 лв

Toofan Shakespeare

С меки корици

13.61 € 26.63 лв

Catholic: an Essential and Exclusive Attribute of the True Church T. J. (Thomas John) 1836-1911 Capel

С меки корици

22.97 € 44.92 лв

Winx Club Book Vol. 5 RAINBOW SPA

С меки корици

12.02 € 23.51 лв

Irish Terrier Training Guide Irish Terrier Training Includes Kevin Cornish

С меки корици

10.79 € 21.10 лв

Measure and Integration Satya N. Mukhopadhyay

С твърди корици

105.66 € 206.65 лв

Jovenes En La Costa Occidental de Huelva Raquel Moura Calvo

С меки корици

145.85 € 285.25 лв

Perspectives on Labour Law A. C. L. Davies

С твърди корици

91.11 € 178.20 лв

Time and Narrative in Ancient Historiography Jonas GrethleinChristopher B. Krebs

С твърди корици

119.69 € 234.09 лв

Due to the growing need for security applications,§speaker recognition as the biometric task of§authenticating a claimant by voice has currently§become a focus of interest.§In this book we present new approaches to integrate§discriminative classifiers like Support Vector§Machines (SVMs) and Sparse Kernel Logistic Regression§(SKLR) into speaker recognition systems that are§traditionally based on generative classifiers like§Gaussian Mixture Models (GMMs).§In a first approach for limited training data the§discriminative classifiers are applied directly on§feature vectors from parameterized speech frames and§it is shown that both, SVM as well as SKLR outperform§traditional methods.§In the second approach a state-of-the-art speaker§recognition system for large amount of training data§is designed that combines Gaussian Mixture Models§with discriminative classifiers.§Furthermore, we investigate different feature§extraction methods for speaker recognition on large§amount of training data and it is shown that the§application of fusion schemes that combine these§subsystems yield a significant improvement of the§recognition performance in comparison to the§application of single subsystems.