Confidence measure for rejection of incorrectly recognized words

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F03%3A00000194" target="_blank" >RIV/49777513:23520/03:00000194 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Confidence measure for rejection of incorrectly recognized words

Popis výsledku v původním jazyce

This paper wishes to contribute to the research activities in the field of detection of incorrectly recognized words during automatic speech recognition. In this paper we describe our original detection technique of incorrectly recognized words and compare it to the one we previously used. Our speech recognition system is based on a speaker-independent continuous density Hidden Markov Model and a dedicated phone sequence recognizing network, which we call a mumble model. The incorrectly recognized word detection method is fully statistically based and uses a MLE (EM) approach to estimate the parameters of statistical models determining the confidence of automatic speech recognition results. We use two kinds of models: the acceptation model and the rejection model. According to their names, the acceptation model corresponds to the words that were correctly recognized, while the rejection one represents all other words, i.e. the misrecognized and out of vocabulary words, they cannot b

Název v anglickém jazyce

Confidence measure for rejection of incorrectly recognized words

Popis výsledku anglicky

This paper wishes to contribute to the research activities in the field of detection of incorrectly recognized words during automatic speech recognition. In this paper we describe our original detection technique of incorrectly recognized words and compare it to the one we previously used. Our speech recognition system is based on a speaker-independent continuous density Hidden Markov Model and a dedicated phone sequence recognizing network, which we call a mumble model. The incorrectly recognized word detection method is fully statistically based and uses a MLE (EM) approach to estimate the parameters of statistical models determining the confidence of automatic speech recognition results. We use two kinds of models: the acceptation model and the rejection model. According to their names, the acceptation model corresponds to the words that were correctly recognized, while the rejection one represents all other words, i.e. the misrecognized and out of vocabulary words, they cannot b

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2003

Kód důvěrnosti údajů

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

Název statě ve sborníku

ECMS 2003

ISBN

80-7083-708-X

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

7-11

Název nakladatele

Technical University

Místo vydání

Liberec

Místo konání akce

Liberec

Datum konání akce

2. 6. 2003

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—