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%3APU49294" target="_blank" >RIV/00216305:26230/04:PU49294 - isvavai.cz</a>
Alternative codes found
RIV/00216305:26230/04:PU50031
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

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

Article name in the collection
Proceedings of 7th International Conference Text,Speech and Dialoque 2004
ISBN
3-540-23049-1
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
465-472
Publisher name
Springer Verlag
Place of publication
Brno
Event location
Brno
Event date
Sep 8, 2004
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)