Keyword classification trees for speech understanding systems
Speech understanding systems try to extract meaning from one or several word sequences hypotheses generated by a speech recognizer. Designers of these systems rely increasingly on robust matchers to perform this task; a robust matcher processes semantically important word islands rather than attempt...
Main Author: | |
---|---|
Other Authors: | |
Format: | Others |
Language: | en |
Published: |
McGill University
1993
|
Subjects: | |
Online Access: | http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=41238 |
id |
ndltd-LACETR-oai-collectionscanada.gc.ca-QMM.41238 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-LACETR-oai-collectionscanada.gc.ca-QMM.412382014-02-13T04:01:02ZKeyword classification trees for speech understanding systemsKuhn, RolandComputer Science.Speech understanding systems try to extract meaning from one or several word sequences hypotheses generated by a speech recognizer. Designers of these systems rely increasingly on robust matchers to perform this task; a robust matcher processes semantically important word islands rather than attempting to parse the entire word sequence. This thesis describes a robust matcher for speech understanding whose rules are learned automatically from training data. Learning is carried out by a new set of algorithms involving a new data structure, the Keyword Classification Tree (KCT). By eliminating the need to handcode and debug a large number of rules, this approach facilitates rapid construction of a speech understanding system. Furthermore, the rules learned by a KCT, which depend on a very small number of words in each utterance, are highly resistant to errors by the speaker or by the speech recognizer. The thesis discusses a speech understanding system built at the Centre de Recherche Informatique de Montreal that incorporates this robust matcher, using the DARPA-sponsored Air Travel Information System (ATIS) task as training corpus and testbed.McGill UniversityMori, Renato De (advisor)1993Electronic Thesis or Dissertationapplication/pdfenalephsysno: 001358952proquestno: NN91711Theses scanned by UMI/ProQuest.All items in eScholarship@McGill are protected by copyright with all rights reserved unless otherwise indicated.Doctor of Philosophy (School of Computer Science.) http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=41238 |
collection |
NDLTD |
language |
en |
format |
Others
|
sources |
NDLTD |
topic |
Computer Science. |
spellingShingle |
Computer Science. Kuhn, Roland Keyword classification trees for speech understanding systems |
description |
Speech understanding systems try to extract meaning from one or several word sequences hypotheses generated by a speech recognizer. Designers of these systems rely increasingly on robust matchers to perform this task; a robust matcher processes semantically important word islands rather than attempting to parse the entire word sequence. This thesis describes a robust matcher for speech understanding whose rules are learned automatically from training data. Learning is carried out by a new set of algorithms involving a new data structure, the Keyword Classification Tree (KCT). By eliminating the need to handcode and debug a large number of rules, this approach facilitates rapid construction of a speech understanding system. Furthermore, the rules learned by a KCT, which depend on a very small number of words in each utterance, are highly resistant to errors by the speaker or by the speech recognizer. The thesis discusses a speech understanding system built at the Centre de Recherche Informatique de Montreal that incorporates this robust matcher, using the DARPA-sponsored Air Travel Information System (ATIS) task as training corpus and testbed. |
author2 |
Mori, Renato De (advisor) |
author_facet |
Mori, Renato De (advisor) Kuhn, Roland |
author |
Kuhn, Roland |
author_sort |
Kuhn, Roland |
title |
Keyword classification trees for speech understanding systems |
title_short |
Keyword classification trees for speech understanding systems |
title_full |
Keyword classification trees for speech understanding systems |
title_fullStr |
Keyword classification trees for speech understanding systems |
title_full_unstemmed |
Keyword classification trees for speech understanding systems |
title_sort |
keyword classification trees for speech understanding systems |
publisher |
McGill University |
publishDate |
1993 |
url |
http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=41238 |
work_keys_str_mv |
AT kuhnroland keywordclassificationtreesforspeechunderstandingsystems |
_version_ |
1716643327018795008 |