Controllare lo stato dell'ordine

Entra a far parte di una comunità di amanti dei libri di tutto il mondo e ottieni numerosi vantaggi. Crea un account gratuito

Punto Poste 5.49 € Punto Poste 5.49 € Corriere DHL 6.99 € Corriere GLS 5.99 € Punto GLS 4.49 € Corriere Bartolini 4.49 € Punto Bartolini 3.49 €

Contatto

Come acquistare

Aiuto

Il mio account

▸ Vuoto :-(

Speech Recognition-Synthesis System for Amharic

Name: Speech Recognition-Synthesis System for Amharic
Brand: TUDpress Verlag der Wissenschaften GmbH
SKU: 09160436
Price: 31.09 EUR
Availability: InStock
Author: Yitagessu B. Gebremedhin
ISBN: 9783944331140

A Unified HMM Based Approach

Yitagessu B. Gebremedhin

Lingua

Inglese

Libro In brossura

Codice Libristo: 09160436

Casa editrice TUDpress Verlag der Wissenschaften GmbH, maggio 2013

Amharic is the official language of Ethiopia and one of the most under-resourced languages in the wo... Descrizione completa

Codice Libristo: 09160436

76 b

31.09 €

Magazzino esterno Inviamo tra 8-11 giorni

Fino a 30 giorni per il reso

I clienti hanno acquistato anche

Influências Greco-romanas na Hispânia: Natália Munaro de Leão

In brossura

69.79 €

Evangelización en los espacios públicos urbanos: evangelización en los mercados de Ghana

In brossura

51.99 €

Black Man's Pride 2 (Studio One) Soul Jazz Records Presents/Various

CD audio

22.59 €

Collection de Poemes Francais Du Xiie Et Du Xiiie Siecles, Partie 1 HIPPEAU-C

In brossura

20.59 €

Analyse de l''introduction de l''edi Dans Les Entreprises Congolaises Alphonse Ivinza Lepapa

In brossura

76.09 €

El saqueo de Marbella : el libro de las agendas secretas de Roca Cristóbal Toro Ortiz

In brossura

15.39 €

Erfolgsfaktor Zeit Quick Response Manufacturing Rajan Suri

Rigido

31.09 €

Amharic is the official language of Ethiopia and one of the most under-resourced languages in the world. The first part of this thesis deals with development of a syllable based ASR system for Amharic. It is demonstrated that a smaller number of acoustic models are sufficient to build a syllable based, speaker independent, continuous, Amharic ASR. It is built for weather forecast and business report applications using the UASR tool kit. A speech corpus of more than 35 hours duration was recorded in three different environments. The grammar is finite state transducer based and the lexical model consists of thousands of words. Though acoustic models for only 93 syllables are trained, a recognition accuracy of 93% is achieved. In the second part of this thesis, development of a parametric unit selection-based speech synthesis for the Amharic language is explained. A speech corpus uttered by a single male speaker is used to train the HMMs. The final section analyzes a corpus of read Amharic speech and surveys syllable-based prosodic variations in F0, duration and intensity to develop suitable prosody models for speech synthesis and recognition.