Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00196164" target="_blank" >RIV/68407700:21230/12:00196164 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR
Original language description
This paper describes the analysis of the performance of MLLR-based speaker adaptation in a large vocabulary continuous speech recognition system. Two different approaches of clustering in MLLR-adaptation with more regression classes, knowledge-based clustering and automatic clustering were analysed. The contribution of mentioned acoustic model adaptation using these two clustering approaches were compared based on the word error rate ratio (WERR) of target LVCSR. Realized study proved that the knowledge-based clustering may bring improvement comparable to the tree-based clustering, when only a few transformation classes are manually defined.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JA - Electronics and optoelectronics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
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
2012 International Conference on Applied Electronics
ISBN
978-80-261-0038-6
ISSN
1803-7232
e-ISSN
—
Number of pages
4
Pages from-to
33-36
Publisher name
University of West Bohemia
Place of publication
Pilsen
Event location
Plzeň
Event date
Sep 6, 2012
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
000305136600002