Robust statistic estimates for adaptation in the task of speech recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F10%3A00504214" target="_blank" >RIV/49777513:23520/10:00504214 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Robust statistic estimates for adaptation in the task of speech recognition

Popis výsledku v původním jazyce

This paper deals with robust estimations of data statistics used for the adaptation. The statistics are accumulated before the adaptation process from available adaptation data. In general, only small amount of adaptation data is assumed. These data areoften corrupted by noise, channel, they do not contain only clean speech. Also, when training Hidden Markov Models (HMM) several assumptions are made that could not have been fulfilled in the praxis, etc. Therefore, we described several techniques that aim to make the adaptation as robust as possible in order to increase the accuracy of the adapted system. One of the methods consists in initialization of the adaptation statistics in order to prevent ill-conditioned transformation matrices. Another problem arises when an acoustic feature is assigned to an improper HMM state even if the reference transcription is available. Such situations can occur because of the forced alignment process used to align frames to states. Thus, it is quite

Název v anglickém jazyce

Robust statistic estimates for adaptation in the task of speech recognition

Popis výsledku anglicky

This paper deals with robust estimations of data statistics used for the adaptation. The statistics are accumulated before the adaptation process from available adaptation data. In general, only small amount of adaptation data is assumed. These data areoften corrupted by noise, channel, they do not contain only clean speech. Also, when training Hidden Markov Models (HMM) several assumptions are made that could not have been fulfilled in the praxis, etc. Therefore, we described several techniques that aim to make the adaptation as robust as possible in order to increase the accuracy of the adapted system. One of the methods consists in initialization of the adaptation statistics in order to prevent ill-conditioned transformation matrices. Another problem arises when an acoustic feature is assigned to an improper HMM state even if the reference transcription is available. Such situations can occur because of the forced alignment process used to align frames to states. Thus, it is quite

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2010

Kód důvěrnosti údajů

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

Název periodika

Lecture Notes in Artificial Intelligence

ISSN

0302-9743

e-ISSN

—

Svazek periodika

2010

Číslo periodika v rámci svazku

6231

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

8

Strana od-do

—

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—