Hierarchical Neural Net Architectures for Feature Extraction in ASR
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F10%3APU89638" target="_blank" >RIV/00216305:26230/10:PU89638 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Hierarchical Neural Net Architectures for Feature Extraction in ASR
Original language description
The paper is on the incorporation of Bottle-Neck features into hierarchical architecture of classifiers. This architecture was used for feature extraction for LVCSR of meetings and the resulting features were evaluated on NIST RT'05 and RT'07 test sets.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GP102%2F09%2FP635" target="_blank" >GP102/09/P635: Theory and applications of phoneme posterior estimation in speech processing</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2010
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)
ISBN
978-1-61782-123-3
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
1201-1204
Publisher name
International Speech Communication Association
Place of publication
Makuhari, Chiba
Event location
Tokyo
Event date
Sep 26, 2010
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—