Fast speaker adaptation in automatic online subtitling
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F09%3A00501738" target="_blank" >RIV/49777513:23520/09:00501738 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Fast speaker adaptation in automatic online subtitling
Original language description
This paper deals with speaker adaptation techniques well suited for the task of online subtitling. Two methods are briefly discussed, namely MAP adaptation and fMLLR. The main emphasis is laid on the description of improvements involved in the process ofadaptation subject to the time requirements. Since the adaptation data are gathered continuously, simple modifications of the accumulated statistics have to be carried out in order to make the adaptation more accurate. Another proposed improvement efficiently employs the combination of fMLLR and MAP. In the case of online adaptation no prior transcriptions of the data are available. They are handled by a recognition system, thus it is suitable to assign a well-applied confidence measure to each of thetranscriptions. We have performed experiments focused on the trade-off between the adaptation speed and the amount of adaptation data. We were able to gain a relative reduction of WER 16.2 %.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
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)
Others
Publication year
2009
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 International Conference on Signal Processing and Multimedia Applications
ISBN
978-989-674-007-8
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
—
Publisher name
INSTICC
Place of publication
Setúbal
Event location
Miláno
Event date
Jul 10, 2009
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—