Intonation Based Sentence Modality Classifier for Czech Using Artificial Neural Network

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F11%3A00183476" target="_blank" >RIV/68407700:21230/11:00183476 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Intonation Based Sentence Modality Classifier for Czech Using Artificial Neural Network

Popis výsledku v původním jazyce

This paper presents an idea and first results of sentence modality classifier for Czech based purely on intonational information. This is in contrast with other studies which usually use more features (including lexical features) for this type of classification. As the sentence melody (intonation) is the most important feature, all the experiments were done on an annotated sample of Czech audiobooks library recorded by Czech leading actors. A non-linear model implemented by artificial neural network (ANN) was chosen for the classification. Two types of ANN are considered in this work in terms of temporal pattern classifications - classical multi-layer perceptron (MLP) network and Elman's network, results for MLP are presented. Pre-processing of temporal intonational patterns for use as ANN inputs is discussed. Results show that questions are very often misclassified as statements and exclamation marks are not detectable in current data set.

Název v anglickém jazyce

Intonation Based Sentence Modality Classifier for Czech Using Artificial Neural Network

Popis výsledku anglicky

This paper presents an idea and first results of sentence modality classifier for Czech based purely on intonational information. This is in contrast with other studies which usually use more features (including lexical features) for this type of classification. As the sentence melody (intonation) is the most important feature, all the experiments were done on an annotated sample of Czech audiobooks library recorded by Czech leading actors. A non-linear model implemented by artificial neural network (ANN) was chosen for the classification. Two types of ANN are considered in this work in terms of temporal pattern classifications - classical multi-layer perceptron (MLP) network and Elman's network, results for MLP are presented. Pre-processing of temporal intonational patterns for use as ANN inputs is discussed. Results show that questions are very often misclassified as statements and exclamation marks are not detectable in current data set.

Druh

D - Stať ve sborníku

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2011

Kód důvěrnosti údajů

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

Název statě ve sborníku

Advances in Nonlinear Speech Processing

ISBN

978-3-642-25019-4

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

162-169

Název nakladatele

Springer

Místo vydání

Heidelberg

Místo konání akce

Las Palmas de Gran Canaria

Datum konání akce

7. 11. 2011

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—