Multilingual acoustic modeling for speech recognition based on Subspace Gaussian Mixture Models
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F10%3APU91981" target="_blank" >RIV/00216305:26230/10:PU91981 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Multilingual acoustic modeling for speech recognition based on Subspace Gaussian Mixture Models
Original language description
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approach has been to use some kind of "universal phone set" that coversmultiple languages. We report experiments on a different approach to multilingual speech recognition, in which the phone sets are entirely distinct but the model has parameters not tied to specific states that are shared across languages. We use a modelcalled a "Subspace Gaussian Mixture Model" where states' distributions are Gaussian Mixture Models with a common structure, constrained to lie in a subspace of the total parameter space. The parameters that define this subspace can be shared across languages. We obtain substantial WER improvements with this approach, especially with very small amounts of inlanguage training data.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/FR-TI1%2F034" target="_blank" >FR-TI1/034: Multilingual recognition and search in speech for electronic dicionaries</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
Proc. International Conference on Acoustictics, Speech, and Signal Processing
ISBN
978-1-4244-4296-6
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
—
Publisher name
IEEE Signal Processing Society
Place of publication
Dallas
Event location
Dallas
Event date
Mar 14, 2010
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—