Fitting class-based language models into weighted finite-state transducer framework

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F03%3A00000158" target="_blank" >RIV/49777513:23520/03:00000158 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Fitting class-based language models into weighted finite-state transducer framework

Original language description

In our paper we propose a general way of incorporating class-based language models with many-to-many word-to-class mapping into the finite-state transducer (FST) framework. Since class-based models alone usually do not improve the recognition accuracy ,we also present a method for an efficient language model combination. An example of a word-to-class mapping based on morphological tags is also given. Several word-based and tag-based language models are tested in the task of transcribing Czech b roadcast news. Results show that class-based models help to achieve a moderate improvement in recognition accuracy.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/LN00A063" target="_blank" >LN00A063: Centre of Computational Linguistics</a><br>

Continuities

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

Publication year

2003

Confidentiality

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

Article name in the collection

EUROSPEECH 2003 PROCEEDINGS

ISBN

—

ISSN

—

e-ISSN

—

Number of pages

4

Pages from-to

1873-1876

Publisher name

ISCA

Place of publication

Geneva

Event location

Geneva

Event date

Sep 1, 2003

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—