Word-subword based keyword spotting with implications in OOV detection

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F10%3APU89665" target="_blank" >RIV/00216305:26230/10:PU89665 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Word-subword based keyword spotting with implications in OOV detection

Original language description

Main-stream systems for keyword spotting and spoken term detection are based on the series of Large Vocabulary Continuous Speech Recognizer with subsequent search in its output. These systems are limited by the vocabulary of the recognizer and are not able to detect Out of Vocabulary (OOV) words. This talk will present our work in designing hybrid word-subword keyword spotting systems, that maintain the accuracy of LVCSR, while allowing for detecting OOVs as sequences of sub-word units. We will also show the links of this work to the detection, description and clustering of OOVs, as investigated in the framework of the EC-sponsored project DIRAC.

Czech name

—

Czech description

—

Type

A - Audiovisual production

CEP classification

IN - Informatics

OECD FORD branch

—

Project

<a href="/en/project/VD20072010B16" target="_blank" >VD20072010B16: Overcoming language barrier that complicates investigation of terrorism financing and relevant financial criminality</a><br>

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2010

Confidentiality

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

ISBN

—

Place of publication

—

Publisher/client name

—

Version

—

Carrier ID

—