Robust Neural Network-Based Estimation of Articulatory Features for Czech

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00221424" target="_blank" >RIV/68407700:21230/14:00221424 - isvavai.cz</a>

Výsledek na webu

<a href="http://nnw.cz/obsahy14.html#5-2014" target="_blank" >http://nnw.cz/obsahy14.html#5-2014</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.14311/NNW.2014.24.027" target="_blank" >10.14311/NNW.2014.24.027</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Robust Neural Network-Based Estimation of Articulatory Features for Czech

Popis výsledku v původním jazyce

The article describes a neural network-based articulatory feature (AF) estimation for the Czech speech. First, the relationship between AFs and a Czech phone inventory is defined, and then the estimation based on the MLP neural networks is done. The usage of several speech representations on the input of the MLP classifiers is proposed with the purpose to obtain a robust AF estimation. The realized experiments have proved that an ANN- based AF estimation works very reliably especially in a low noise environment. Moreover, in case the number of neurons in a hidden layer is increased and if the temporal context DCT-TRAP features are used on the input of the MLP network, the AF classification works accurately also for the signals collected in the environments with a high background noise.

Název v anglickém jazyce

Robust Neural Network-Based Estimation of Articulatory Features for Czech

Popis výsledku anglicky

The article describes a neural network-based articulatory feature (AF) estimation for the Czech speech. First, the relationship between AFs and a Czech phone inventory is defined, and then the estimation based on the MLP neural networks is done. The usage of several speech representations on the input of the MLP classifiers is proposed with the purpose to obtain a robust AF estimation. The realized experiments have proved that an ANN- based AF estimation works very reliably especially in a low noise environment. Moreover, in case the number of neurons in a hidden layer is increased and if the temporal context DCT-TRAP features are used on the input of the MLP network, the AF classification works accurately also for the signals collected in the environments with a high background noise.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Neural Network World

ISSN

1210-0552

e-ISSN

—

Svazek periodika

24

Číslo periodika v rámci svazku

5

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

16

Strana od-do

463-478

Kód UT WoS článku

000344832300003

EID výsledku v databázi Scopus

—