Modelování neřečových událostí řečníka při robustním rozpoznávání řeči

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F06%3A03129459" target="_blank" >RIV/68407700:21230/06:03129459 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Modelling of Speaker Non-speech Events in Robust Speech Recognition

Popis výsledku v původním jazyce

Experiments on modelling of speaker non-speech events (SNE) using robust speech recogniser based on hidden Markov models (HMM) are presented in this work. A speaker independent spoken Czech digits recogniser based on Czech phoneme modelling in real environment was used for this purpose. Only SNEs which are positioned in between words are modelled, as they can be easily added to the recogniser grammar as they were another word. The recognition results were analysed for two different testing datasets, each derived from the training sets (different in environmental conditions). At the end of the experiment the recognition score increased for about 22% and 11% for the used testing datasets against the results reached without modelling the events. The recogniser was also tested on data with unknown recording conditions. Low number of incorrectly inserted word shows that this modelling seem to be less dependent on recording conditions than pure phoneme model case.

Název v anglickém jazyce

Modelling of Speaker Non-speech Events in Robust Speech Recognition

Popis výsledku anglicky

Experiments on modelling of speaker non-speech events (SNE) using robust speech recogniser based on hidden Markov models (HMM) are presented in this work. A speaker independent spoken Czech digits recogniser based on Czech phoneme modelling in real environment was used for this purpose. Only SNEs which are positioned in between words are modelled, as they can be easily added to the recogniser grammar as they were another word. The recognition results were analysed for two different testing datasets, each derived from the training sets (different in environmental conditions). At the end of the experiment the recognition score increased for about 22% and 11% for the used testing datasets against the results reached without modelling the events. The recogniser was also tested on data with unknown recording conditions. Low number of incorrectly inserted word shows that this modelling seem to be less dependent on recording conditions than pure phoneme model case.

Druh

D - Stať ve sborníku

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

<a href="/cs/project/GD102%2F03%2FH085" target="_blank" >GD102/03/H085: Modelování biologických a řečových signálů</a><br>

Návaznosti

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

Rok uplatnění

2006

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 16th Czech-German Workshop on Speech Processing

ISBN

80-86269-15-9

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

149-155

Název nakladatele

AV ČR, Ústav radiotechniky a elektroniky

Místo vydání

Praha

Místo konání akce

Praha

Datum konání akce

27. 9. 2006

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—