DMCA
Evaluating speech-driven web retrieval in the third NTCIR workshop (2003)
| Venue: | in Proc. AAAI Spring Symposium: Intelligent Multimedia Knowledge Management |
| Citations: | 1 - 0 self |
BibTeX
@INPROCEEDINGS{Fujii03evaluatingspeech-driven,
author = {Atsushi Fujii and Katunobu Itou},
title = {Evaluating speech-driven web retrieval in the third NTCIR workshop},
booktitle = {in Proc. AAAI Spring Symposium: Intelligent Multimedia Knowledge Management},
year = {2003}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Speech recognition has of late become a practical technology for real world applications. For the purpose of research and development in speech-driven retrieval, which facilitates re-trieving information with spoken queries, we organized the speech-driven retrieval subtask in the NTCIR-3 Web retrieval task. Search topics for the Web retrieval main task were dic-tated by ten speakers and were recorded as collections of spo-ken queries. We used those queries to evaluate the perfor-mance of our speech-driven retrieval system, in which speech recognition and text retrieval modules were integrated. The text retrieval module, which is based on a probabilistic model, indexed only textual contents in documents (Web pages), but did not use HTML tags and hyperlink information in docu-ments. Experimental results showed that a) the use of target documents for language modeling and b) enhancement of the vocabulary size in speech recognition were effective to im-prove the system performance.
Keyphrases
speech recognition speech-driven web retrieval third ntcir workshop text retrieval module web page real world application speech-driven retrieval subtask spo-ken query re-trieving information spoken query textual content late become html tag ten speaker target document system performance ntcir-3 web retrieval task speech-driven retrieval vocabulary size web retrieval main task search topic practical technology probabilistic model speech-driven retrieval system language modeling experimental result
