Robust Techniques for Organizing and Retrieving Spoken Documents

Robust Techniques for Organizing and Retrieving Spoken Documents

<p/> <p>Information retrieval tasks such as document retrieval and topic detection and tracking (TDT) show little degradation when applied to speech recognizer output. We claim that the robustness of the process is because of inherent redundancy in the problem: not only are words repeate...

Full description

Bibliographic Details
Main Author: Allan James
Format: Article
Language:English
Published: SpringerOpen 2003-01-01
Series:EURASIP Journal on Advances in Signal Processing
Subjects:
spoken document retrieval
topic detection and tracking
information retrieval
Online Access:http://dx.doi.org/10.1155/S1110865703211070
id doaj-b48d2a704a3d497c9fd6d3563ccba244
record_format Article
spelling doaj-b48d2a704a3d497c9fd6d3563ccba2442020-11-24T21:19:08ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802003-01-0120032980946Robust Techniques for Organizing and Retrieving Spoken DocumentsAllan James<p/> <p>Information retrieval tasks such as document retrieval and topic detection and tracking (TDT) show little degradation when applied to speech recognizer output. We claim that the robustness of the process is because of inherent redundancy in the problem: not only are words repeated, but semantically related words also provide support. We show how document and query expansion can enhance that redundancy and make document retrieval robust to speech recognition errors. We show that the same effect is true for TDT&#8242;s tracking task, but that recognizer errors are more of an issue for new event and story link detection.</p>http://dx.doi.org/10.1155/S1110865703211070spoken document retrievaltopic detection and trackinginformation retrieval
collection DOAJ
language English
format Article
sources DOAJ
author Allan James
spellingShingle Allan James
Robust Techniques for Organizing and Retrieving Spoken Documents
EURASIP Journal on Advances in Signal Processing
spoken document retrieval
topic detection and tracking
information retrieval
author_facet Allan James
author_sort Allan James
title Robust Techniques for Organizing and Retrieving Spoken Documents
title_short Robust Techniques for Organizing and Retrieving Spoken Documents
title_full Robust Techniques for Organizing and Retrieving Spoken Documents
title_fullStr Robust Techniques for Organizing and Retrieving Spoken Documents
title_full_unstemmed Robust Techniques for Organizing and Retrieving Spoken Documents
title_sort robust techniques for organizing and retrieving spoken documents
publisher SpringerOpen
series EURASIP Journal on Advances in Signal Processing
issn 1687-6172
1687-6180
publishDate 2003-01-01
description <p/> <p>Information retrieval tasks such as document retrieval and topic detection and tracking (TDT) show little degradation when applied to speech recognizer output. We claim that the robustness of the process is because of inherent redundancy in the problem: not only are words repeated, but semantically related words also provide support. We show how document and query expansion can enhance that redundancy and make document retrieval robust to speech recognition errors. We show that the same effect is true for TDT&#8242;s tracking task, but that recognizer errors are more of an issue for new event and story link detection.</p>
topic spoken document retrieval
topic detection and tracking
information retrieval
url http://dx.doi.org/10.1155/S1110865703211070
work_keys_str_mv AT allanjames robusttechniquesfororganizingandretrievingspokendocuments
_version_ 1726006860092276736

Similar Items