Data adaptation for Hidden Markov Model in speech recognition

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F02%3APU28123" target="_blank" >RIV/00216305:26220/02:PU28123 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Data adaptation for Hidden Markov Model in speech recognition

Original language description

In Hidden Markov models, speech data are modeled by Gaussian distributions. In this paper, we propose to Gaussianize the features to better fit to this modeling. A distribution of the data is estimated and a transform function is derived. We test three methods of the transform estimation (global, speaker based, frame based) and report results on the SPINE 2000 task with Sphinx recognizer. We conclude that the proposed method is a cheap way to increase the recognition accuracy.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

JA - Electronics and optoelectronics

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2002

Confidentiality

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

Article name in the collection

Proceedings of 8th Conference STUDENT EEICT 2002

ISBN

80-214-2116-9

ISSN

—

e-ISSN

—

Number of pages

4

Pages from-to

317-320

Publisher name

Neuveden

Place of publication

Brno

Event location

FEKT VUT Brno

Event date

Apr 25, 2002

Type of event by nationality

CST - Celostátní akce

UT code for WoS article

—