A Region-specific Feature-space Transformation for Speaker Adaptation and Singularity Analysis of Jacobian Matrix

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F13%3APU106411" target="_blank" >RIV/00216305:26230/13:PU106411 - isvavai.cz</a>
Result on the web
<a href="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/rath_interspeech2013_IS130146.pdf" target="_blank" >http://www.fit.vutbr.cz/research/groups/speech/publi/2013/rath_interspeech2013_IS130146.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
A Region-specific Feature-space Transformation for Speaker Adaptation and Singularity Analysis of Jacobian Matrix
Original language description
This paper describes the difficulties associated with soft R-FMLLR. By analyzing the Jacobian matrix, it was concluded that the transformation is most likely to be non-invertible and in this case ML estimation adversely affects the performance. A new transformation, hard R-FMLLR, is presented. It is shown that the performance of the proposed method is better than soft R-FMLLR and it is computationally more efficient.
Czech name
—
Czech description
—

Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project
<a href="/en/project/TA01011328" target="_blank" >TA01011328: Technologies of speech processing for efficient human-machine communication</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)