Robust Adaptation Techniques Dealing with Small Amount of Data

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F12%3A43915990" target="_blank" >RIV/49777513:23520/12:43915990 - isvavai.cz</a>

Result on the web

<a href="http://download.springer.com/static/pdf/237/chp%253A10.1007%252F978-3-642-32790-2_58.pdf?auth66=1352100308_6ca3feab5ab1f038650cd3b971c1f53b&ext=.pdf" target="_blank" >http://download.springer.com/static/pdf/237/chp%253A10.1007%252F978-3-642-32790-2_58.pdf?auth66=1352100308_6ca3feab5ab1f038650cd3b971c1f53b&ext=.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Robust Adaptation Techniques Dealing with Small Amount of Data

Original language description

The worst problem the adaptation is dealing with is the lack of adaptation data. This work focuses on the feature Maximum Likelihood Linear Regression (fMLLR) adaptation where the number of free parameters to be estimated significantly decreases in comparison with other adaptation methods. However, the number of free parameters of fMLLR transform is still too high to be estimated properly when dealing with extremely small data sets. We described and compared various methods used to avoid this problem, namely the initialization of the fMLLR transform and a linear combination of basis matrices varying in the choice of the basis estimation (eigen decomposition, factor analysis, independent component analysis and maximum likelihood estimation). Initialization methods compensate the absence of the test speaker's data utilizing other suitable data. Methods using linear combination of basis matrices reduce the number of estimated fMLLR parameters to a smaller number of weights to be estimated

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/DF12P01OVV022" target="_blank" >DF12P01OVV022: ASR- and MT-based Access to a Large Archive of Cultural Heritage (AMALACH)</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2012

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Lecture Notes in Computer Science

ISSN

0302-9743

e-ISSN

—

Volume of the periodical

7499

Issue of the periodical within the volume

neuveden

Country of publishing house

DE - GERMANY

Number of pages

8

Pages from-to

480-487

UT code for WoS article

—

EID of the result in the Scopus database

—