Accuracy Analysis of Generalized Pronunciation Variant Selection in ASR Systems

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F09%3A00157411" target="_blank" >RIV/68407700:21230/09:00157411 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Accuracy Analysis of Generalized Pronunciation Variant Selection in ASR Systems

Original language description

Automated speech recognition (ASR) systems work typically with pronunciation dictionary for generating expected phonetic content of particular words in recognized utterance. But the pronunciation can vary in many situations. Besides the cases with more possible pronunciation variants specified manually in the dictionary there are typically many other possible changes in the pronunciation depending on word context or speaking style, very typical for our case of Czech language. In this paper we have studied the accuracy of proper selection of automatically predicted pronunciation variants in Czech HMM ASR based systems. We have analyzed correctness of pronunciation variant selection in forced alignment of known utterances. Using the proper pronunciationvariant were created mainly for the more accurate training of acoustic HMM models. Finally, the accuracy of LVCSR results using different levels of automated pronunciation generation were tested.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JA - Electronics and optoelectronics

OECD FORD branch

—

Project

<a href="/en/project/GA102%2F08%2F0707" target="_blank" >GA102/08/0707: Speech Recognition under Real-World Conditions</a><br>

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2009

Confidentiality

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

Name of the periodical

Lecture Notes in Artificial Intelligence

ISSN

0302-9743

e-ISSN

—

Volume of the periodical

5641

Issue of the periodical within the volume

2009931057

Country of publishing house

DE - GERMANY

Number of pages

10

Pages from-to

—

UT code for WoS article

—

EID of the result in the Scopus database

—