Semantic Entity Detection From Multiple ASR Hypotheses Within The WFST Framework

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F13%3A43920759" target="_blank" >RIV/49777513:23520/13:43920759 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ASRU.2013.6707710" target="_blank" >http://dx.doi.org/10.1109/ASRU.2013.6707710</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ASRU.2013.6707710" target="_blank" >10.1109/ASRU.2013.6707710</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Semantic Entity Detection From Multiple ASR Hypotheses Within The WFST Framework

Popis výsledku v původním jazyce

The paper presents a novel approach to named entity detection from ASR lattices. Since the described method not only detects the named entities but also assigns a detailed semantic interpretation to them, we call our approach the semantic entity detection. All the algorithms are designed to use automata operations defined within the framework of weighted finite state transducers (WFST) the ASR lattices are nowadays frequently represented as weighted acceptors. The expert knowledge about the semantics ofthe task at hand can be first expressed in the form of a context free grammar and then converted to the FST form. We use a WFST optimization to obtain compact representation of the ASR lattice. The WFST framework also allows to use the word confusion networks as another representation of multiple ASR hypotheses. That way we can use the full power of composition and optimization operations implemented in the OpenFST toolkit for our semantic entity detection algorithm. The devised method

Název v anglickém jazyce

Semantic Entity Detection From Multiple ASR Hypotheses Within The WFST Framework

Popis výsledku anglicky

The paper presents a novel approach to named entity detection from ASR lattices. Since the described method not only detects the named entities but also assigns a detailed semantic interpretation to them, we call our approach the semantic entity detection. All the algorithms are designed to use automata operations defined within the framework of weighted finite state transducers (WFST) the ASR lattices are nowadays frequently represented as weighted acceptors. The expert knowledge about the semantics ofthe task at hand can be first expressed in the form of a context free grammar and then converted to the FST form. We use a WFST optimization to obtain compact representation of the ASR lattice. The WFST framework also allows to use the word confusion networks as another representation of multiple ASR hypotheses. That way we can use the full power of composition and optimization operations implemented in the OpenFST toolkit for our semantic entity detection algorithm. The devised method

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/TE01020197" target="_blank" >TE01020197: Centrum aplikované kybernetiky 3</a><br>

Návaznosti

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

Rok uplatnění

2013

Kód důvěrnosti údajů

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

Název statě ve sborníku

IEEE 2013 Workshop on Automatic Speech Recognition and Understanding

ISBN

978-1-4799-2756-2

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

84-89

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Piscataway

Místo konání akce

Olomouc

Datum konání akce

8. 12. 2013

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—