Region Dependent Linear Transforms in Multilingual Speech Recognition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F12%3APU98188" target="_blank" >RIV/00216305:26230/12:PU98188 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/ICASSP.2012.6289014" target="_blank" >http://dx.doi.org/10.1109/ICASSP.2012.6289014</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP.2012.6289014" target="_blank" >10.1109/ICASSP.2012.6289014</a>
Alternative languages
Result language
angličtina
Original language name
Region Dependent Linear Transforms in Multilingual Speech Recognition
Original language description
In today's speech recognition systems, linear or nonlinear transformations are usually applied to post-process speech features forming input to HMM based acoustic models. In this work, we experiment with three popular transforms: HLDA,MPE-HLDA and RegionDependent Linear Transforms (RDLT), which are trained jointly with the acoustic model to extract maximum of the discriminative information from the raw features and to represent it in a form suitable for the following GMM-HMM based acoustic model. We focus on multi-lingual environments, where limited resources are available for training recognizers of many languages. Using data from GlobalPhone database, we show that, under such restrictive conditions, the feature transformations can be advantageouslyshared across languages and robustly trained using data from several languages.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JC - Computer hardware and software
OECD FORD branch
—
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proc. International Conference on Acoustics, Speech, and Signal Processing 2012
ISBN
978-1-4673-0044-5
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
4885-4888
Publisher name
IEEE Signal Processing Society
Place of publication
Kyoto
Event location
Kyoto
Event date
Mar 25, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000312381404239