A study of different weighting schemes for spoken language understanding based on convolutional neural networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F16%3A43929967" target="_blank" >RIV/49777513:23520/16:43929967 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7472842" target="_blank" >http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7472842</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2016.7472842" target="_blank" >10.1109/ICASSP.2016.7472842</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A study of different weighting schemes for spoken language understanding based on convolutional neural networks

Popis výsledku v původním jazyce

This paper describes the development of a stateless spoken spoken language understanding (SLU) module based on artificial neural networks that is able to deal with the uncertainty of the automatic speech recognition (ASR) output. The work builds upon the concept of weighted neurons introduced by the authors previously and presents a generalized weighting term for such a neuron. The effect of different forms and parameter estimation methods of the weighting term is experimentally evaluated on the multi-task training corpus, created by merging two different semantically annotated corpora. The robustness of the best performing weighting schemes is then demonstrated by experiments involving hybrid word-semantic (WSE) lattices and also limited data scenario.

Název v anglickém jazyce

A study of different weighting schemes for spoken language understanding based on convolutional neural networks

Popis výsledku anglicky

This paper describes the development of a stateless spoken spoken language understanding (SLU) module based on artificial neural networks that is able to deal with the uncertainty of the automatic speech recognition (ASR) output. The work builds upon the concept of weighted neurons introduced by the authors previously and presents a generalized weighting term for such a neuron. The effect of different forms and parameter estimation methods of the weighting term is experimentally evaluated on the multi-task training corpus, created by merging two different semantically annotated corpora. The robustness of the best performing weighting schemes is then demonstrated by experiments involving hybrid word-semantic (WSE) lattices and also limited data scenario.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Centrum pro multi-modální interpretaci dat velkého rozsahu</a><br>

Návaznosti

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

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

2016 IEEE International Conference on Acoustics, Speech, and Signal Processing Proceedings

ISBN

978-1-4799-9988-0

ISSN

2379-190X

e-ISSN

—

Počet stran výsledku

5

Strana od-do

6065-6069

Název nakladatele

IEEE Signal Processing Society

Místo vydání

New York

Místo konání akce

Shanghai, China

Datum konání akce

20. 5. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000388373406044