Hierarchical Discriminative Model for Spoken Language Understanding Based on Convolutional Neural Network
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43926617" target="_blank" >RIV/49777513:23520/15:43926617 - isvavai.cz</a>
Result on the web
<a href="http://www.isca-speech.org/archive/interspeech_2015/papers/i15_1864.pdf" target="_blank" >http://www.isca-speech.org/archive/interspeech_2015/papers/i15_1864.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Hierarchical Discriminative Model for Spoken Language Understanding Based on Convolutional Neural Network
Original language description
This paper presents a novel method for processing automatic speech recognition (ASR) lattices (and generally weighted finite state acceptors) in feed-forward artificial neural networks. It is based on the existing work focused on the text classification using convolutional neural networks (CNNs). The presented method generalizes the convolutional layer of the neural network so that it is able to process both the posterior probabilities and the lexical information contained in an ASR lattice. The convolutional layer was used in a CNN-based implementation of a hierarchical discriminative model (HDM). The method was evaluated using two semantically annotated corpora and the CNN-based HDM improves performance of a spoken language understanding module in comparison with an original HDM based on Support Vector Machines (SVM)
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20205 - Automation and control systems
Result continuities
Project
<a href="/en/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Center for Large Scale Multi-modal Data Interpretation</a><br>
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 16th Annual Conference of the International Speech Communication Association (Interspeech 2015)
ISBN
978-1-5108-1790-6
ISSN
2308-457X
e-ISSN
—
Number of pages
5
Pages from-to
1864-1868
Publisher name
Curran Associates, Inc.
Place of publication
Red Hook, NY
Event location
Dresden, Germany
Event date
Sep 6, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000380581600387