Investigation into the use of deep neural networks for LVCSR of Czech

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F15%3A%230003430" target="_blank" >RIV/46747885:24220/15:#0003430 - isvavai.cz</a>
Alternative codes found
RIV/46747885:24220/15:00002969
Result on the web
<a href="http://dx.doi.org/10.1109/ECMSM.2015.7208708" target="_blank" >http://dx.doi.org/10.1109/ECMSM.2015.7208708</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ECMSM.2015.7208708" target="_blank" >10.1109/ECMSM.2015.7208708</a>

Result language
angličtina
Original language name
Investigation into the use of deep neural networks for LVCSR of Czech
Original language description
This paper deals with utilization of deep neural networks (DNNs) for speech recognition. The main goal is to find out the best strategy for training and utilization of these models within an acoustic modeling module of a large vocabulary continuous speech recognition (LVCSR) system of Czech language. For this purpose, various DNNs are trained a) using several training strategies, b) with different inner structure and c) using various kinds of features. Experimental evaluation is then performed on a large dataset including broadcast recordings, recordings of lectures, dictates of judgments and set of nonlinearly distorted utterances. The resulting recipe for training of DNNs for our LVCSR system employs a) ReLU activation function with hidden layer width of 1024 neurons and b) filter-bank based features.
Czech name
—
Czech description
—

Project
<a href="/en/project/TA04010199" target="_blank" >TA04010199: MULTILINMEDIA - Multilingual Multimedia Monitoring and Analyzing Platform</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
2015 IEEE International Workshop of Electronics, Control, Measurement, Signals and their application to Mechatronics
ISBN
978-1-4799-6972-2
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
38-41
Publisher name
IEEE
Place of publication
Česká Republika
Event location
Česká Republika, Liberec
Event date
Jan 1, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000363814500033

Similar results(10)