Information fusion for spoken document retrieval

Authors:
K. Ng
Affiliations:
Lab. for Comput. Sci., MIT, Cambridge, MA, USA
Venue:
ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 04
Year:
2000

Citing 0
Cited 7

Spoken content metadata and MPEG-7

MULTIMEDIA '00 Proceedings of the 2000 ACM workshops on Multimedia
A hierarchical tag-graph search scheme with layered grammar rules for spontaneous speech understanding

Pattern Recognition Letters
Thematic indexing of spoken documents by using self-organizing maps

Speech Communication
VideoQA: question answering on news video

MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
A new structure for news editing

IBM Systems Journal
A discriminative HMM/N-gram-based retrieval approach for mandarin spoken documents

ACM Transactions on Asian Language Information Processing (TALIP)
Exploring fusion in a spontaneous speech retrieval task

SSCS '09 Proceedings of the third workshop on Searching spontaneous conversational speech

Quantified Score

Hi-index	0.00

Visualization

Abstract

Investigates 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 the 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.