Towards Lower Error Rates in Phoneme Recognition

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F04%3APU49295" target="_blank" >RIV/00216305:26230/04:PU49295 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Towards Lower Error Rates in Phoneme Recognition

Original language description

We investigate techniques for acoustic modeling in automatic recognition of context-independent phoneme strings from the TIMIT database. The baseline phoneme recognizer is based on TempoRAl Patterns (TRAP). This recognizer is simplified to shorten processing times and reduce computational requirements. More states per phoneme and bi-gram language models are incorporated into the system and evaluated. The question of insufficient amount of training data is discussed and the system is improved. All modifiications lead to a faster system with about 23.6% relative improvement over the baseline in phoneme error rate.

Czech name

Postup k nižší chybovosti fonémového rozpoznávače

Czech description

Postup k Nižší Chybovosti Fonémového Rozpoznávače

Type

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

CEP classification

JC - Computer hardware and software

OECD FORD branch

—

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

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

Publication year

2004

Confidentiality

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

Name of the periodical

Lecture Notes in Computer Science

ISSN

0302-9743

e-ISSN

—

Volume of the periodical

2004

Issue of the periodical within the volume

3206

Country of publishing house

DE - GERMANY

Number of pages

8

Pages from-to

465-472

UT code for WoS article

—

EID of the result in the Scopus database

—