DMCA
Information Fusion For Spoken Document Retrieval (2000)
Cached
Download Links
| Venue: | in Proc. ICASSP |
| Citations: | 20 - 0 self |
BibTeX
@INPROCEEDINGS{Ng00informationfusion,
author = {Kenney Ng},
title = {Information Fusion For Spoken Document Retrieval},
booktitle = {in Proc. ICASSP},
year = {2000}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper we investigate the fusion of different information sources with the goal of improving performance on spoken document retrieval (SDR) tasks. In particular, we explore the use of multiple transcriptions from different automatic speech recognizers, the combination of different types of subword unit indexing terms, and the combination of word and subword-based units. To perform retrieval, we use a novel probabilistic information retrieval model which retrieves documents based on maximum likelihood ratio scores. Experiments on the 1998 TREC-7 SDR task show that the use of these different information fusion approaches can result in significantly improved retrieval performance. 1. INTRODUCTION Spoken document retrieval (SDR) is the task of searching a static collection of recorded speech messages in response to a userspecified natural language text query and returning an ordered list of messages ranked according to their relevance to the query. The development of automatic met...
Keyphrases
spoken document retrieval information fusion novel probabilistic information retrieval model different automatic speech recognizers different information source automatic met static collection different information fusion approach different type subword unit indexing term maximum likelihood ratio score subword-based unit recorded speech message retrieval performance introduction spoken document retrieval trec-7 sdr task show userspecified natural language text query ordered list multiple transcription
