Spoken document understanding and organization

Lin Shan Lee, Berlin Chen

Research output: Contribution to journalArticle

109 Citations (Scopus)

Abstract

Spoken documents associated with the network content are critical for retrieval and browsing. An overview is given of various technology areas reaching towards this goal in a unified context. Technology areas covered include named-entity (NE) extraction, segmentation, and information extraction for the spoken documents as well as automatic summarization, title generation, and topic analysis and organization. The relevant problems and issues, general principles, and basic approaches for each area are briefly reviewed. A framework for properly integrating all these different technology areas is proposed, in which four different levels of processes are defined and bottom-up and top-down relationships are discussed. An initial prototype system for such purposes has been developed by National Taiwan University. The resultant system used broadcast news in Mandarin Chinese as example spoken documents.

Original languageEnglish
Pages (from-to)42-60
Number of pages19
JournalIEEE Signal Processing Magazine
Volume22
Issue number5
DOIs
Publication statusPublished - 2005 Jan 1

Fingerprint

Information Extraction
Summarization
Taiwan
Browsing
Bottom-up
Broadcast
Retrieval
Segmentation
Prototype
Context
Relationships
Framework

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Spoken document understanding and organization. / Lee, Lin Shan; Chen, Berlin.

In: IEEE Signal Processing Magazine, Vol. 22, No. 5, 01.01.2005, p. 42-60.

Research output: Contribution to journalArticle

@article{6051125b6f6e4f32a4f7698a978ec0a0,
title = "Spoken document understanding and organization",
abstract = "Spoken documents associated with the network content are critical for retrieval and browsing. An overview is given of various technology areas reaching towards this goal in a unified context. Technology areas covered include named-entity (NE) extraction, segmentation, and information extraction for the spoken documents as well as automatic summarization, title generation, and topic analysis and organization. The relevant problems and issues, general principles, and basic approaches for each area are briefly reviewed. A framework for properly integrating all these different technology areas is proposed, in which four different levels of processes are defined and bottom-up and top-down relationships are discussed. An initial prototype system for such purposes has been developed by National Taiwan University. The resultant system used broadcast news in Mandarin Chinese as example spoken documents.",
author = "Lee, {Lin Shan} and Berlin Chen",
year = "2005",
month = "1",
day = "1",
doi = "10.1109/MSP.2005.1511823",
language = "English",
volume = "22",
pages = "42--60",
journal = "IEEE Signal Processing Magazine",
issn = "1053-5888",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Spoken document understanding and organization

AU - Lee, Lin Shan

AU - Chen, Berlin

PY - 2005/1/1

Y1 - 2005/1/1

N2 - Spoken documents associated with the network content are critical for retrieval and browsing. An overview is given of various technology areas reaching towards this goal in a unified context. Technology areas covered include named-entity (NE) extraction, segmentation, and information extraction for the spoken documents as well as automatic summarization, title generation, and topic analysis and organization. The relevant problems and issues, general principles, and basic approaches for each area are briefly reviewed. A framework for properly integrating all these different technology areas is proposed, in which four different levels of processes are defined and bottom-up and top-down relationships are discussed. An initial prototype system for such purposes has been developed by National Taiwan University. The resultant system used broadcast news in Mandarin Chinese as example spoken documents.

AB - Spoken documents associated with the network content are critical for retrieval and browsing. An overview is given of various technology areas reaching towards this goal in a unified context. Technology areas covered include named-entity (NE) extraction, segmentation, and information extraction for the spoken documents as well as automatic summarization, title generation, and topic analysis and organization. The relevant problems and issues, general principles, and basic approaches for each area are briefly reviewed. A framework for properly integrating all these different technology areas is proposed, in which four different levels of processes are defined and bottom-up and top-down relationships are discussed. An initial prototype system for such purposes has been developed by National Taiwan University. The resultant system used broadcast news in Mandarin Chinese as example spoken documents.

UR - http://www.scopus.com/inward/record.url?scp=85032751176&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032751176&partnerID=8YFLogxK

U2 - 10.1109/MSP.2005.1511823

DO - 10.1109/MSP.2005.1511823

M3 - Article

AN - SCOPUS:85032751176

VL - 22

SP - 42

EP - 60

JO - IEEE Signal Processing Magazine

JF - IEEE Signal Processing Magazine

SN - 1053-5888

IS - 5

ER -