Penalty Functions for Evaluation Measures of Unsegmented Speech Retrieval

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F12%3A10130046" target="_blank" >RIV/00216208:11320/12:10130046 - isvavai.cz</a>

Result on the web

<a href="http://link.springer.com/chapter/10.1007/978-3-642-33247-0_12" target="_blank" >http://link.springer.com/chapter/10.1007/978-3-642-33247-0_12</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-642-33247-0_12" target="_blank" >10.1007/978-3-642-33247-0_12</a>

Result language

angličtina

Original language name

Penalty Functions for Evaluation Measures of Unsegmented Speech Retrieval

Original language description

This paper deals with evaluation of information retrieval from unsegmented speech. We focus on Mean Generalized Average Precision, the evaluation measure widely used for unsegmented speech retrieval. This measure is designed to allow certain tolerance inmatching retrieval results (starting points of relevant segments) against a gold standard relevance assessment. It employs a Penalty Function which evaluates non-exact matches in the retrieval results based on their distance from the beginnings of theirnearest true relevant segments. However, the choice of the Penalty Function is usually ad-hoc and does not necessary re?ect users' perception of the speech retrieval quality. We perform a lab test to study satisfaction of users of a speech retrieval system to empirically estimate the optimal shape of the Penalty Function.

Czech name

—

Czech description

—

Type

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

CEP classification

IN - Informatics

OECD FORD branch

—

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

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

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

7488

Issue of the periodical within the volume

7488

Country of publishing house

DE - GERMANY

Number of pages

12

Pages from-to

100-111

UT code for WoS article

—

EID of the result in the Scopus database

—