OLIVE: Speech-Based Video Retrieval

Franciska M.G. de Jong; Jean-Luc Gauvain; Jurgen den Hartog; Jeremy den Hartog; Klaus Netter

OLIVE: Speech-Based Video Retrieval

Franciska M.G. de Jong, Jean-Luc Gauvain, Jurgen den Hartog, Jeremy den Hartog, Klaus Netter

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

62 Downloads (Pure)

Abstract

This paper describes the Olive project which aims to support automated indexing of video material by use of human language technologies. Olive is making use of speech recognition to automatically derive transcriptions of the sound tracks, generating time-coded linguistic elements which serve as the basis for text-based retrieval functionality. The retrieval demonstrator builds on and extends the architecture from the Pop-Eye project, a system applying human language technology on subtitles for the disclosure of video fragments.

Original language	Undefined
Title of host publication	Proceedings of the 1st European Workshop on Content-Based Multimedia Indexing (CBMI'99)
Place of Publication	Toulouse
Publisher	IRIT
Pages	75-80
Number of pages	6
ISBN (Print)	not assigned
Publication status	Published - Oct 1999
Event	1st European Workshop on Content-Based Multimedia Indexing, CBMI 1999 - IRIT Building, Toulouse, France Duration: 25 Oct 1999 → 27 Oct 1999 Conference number: 1

Publication series

Name
Publisher	IRIT

Workshop

Workshop	1st European Workshop on Content-Based Multimedia Indexing, CBMI 1999
Abbreviated title	CBMI 1999
Country/Territory	France
City	Toulouse
Period	25/10/99 → 27/10/99

Keywords

IR-80669
HMI-MR: MULTIMEDIA RETRIEVAL
EWI-9258
METIS-119718

Access to Document

http://www.eurecom.fr/~bmgroup/cbmi99/technical_program.html

Cite this

@inproceedings{0b00a42e7a194ea1b2ab9a94b1431343,

title = "OLIVE: Speech-Based Video Retrieval",

abstract = "This paper describes the Olive project which aims to support automated indexing of video material by use of human language technologies. Olive is making use of speech recognition to automatically derive transcriptions of the sound tracks, generating time-coded linguistic elements which serve as the basis for text-based retrieval functionality. The retrieval demonstrator builds on and extends the architecture from the Pop-Eye project, a system applying human language technology on subtitles for the disclosure of video fragments.",

keywords = "IR-80669, HMI-MR: MULTIMEDIA RETRIEVAL, EWI-9258, METIS-119718",

author = "{de Jong}, {Franciska M.G.} and Jean-Luc Gauvain and {den Hartog}, Jurgen and {den Hartog}, Jeremy and Klaus Netter",

year = "1999",

month = oct,

language = "Undefined",

isbn = "not assigned",

publisher = "IRIT",

pages = "75--80",

booktitle = "Proceedings of the 1st European Workshop on Content-Based Multimedia Indexing (CBMI'99)",

note = "1st European Workshop on Content-Based Multimedia Indexing, CBMI 1999 ; Conference date: 25-10-1999 Through 27-10-1999",

}

de Jong, FMG, Gauvain, J-L, den Hartog, J, den Hartog, J & Netter, K 1999, OLIVE: Speech-Based Video Retrieval. in Proceedings of the 1st European Workshop on Content-Based Multimedia Indexing (CBMI'99). IRIT, Toulouse, pp. 75-80, 1st European Workshop on Content-Based Multimedia Indexing, CBMI 1999, Toulouse, France, 25/10/99. <http://www.eurecom.fr/~bmgroup/cbmi99/technical_program.html>

TY - GEN

T1 - OLIVE: Speech-Based Video Retrieval

AU - de Jong, Franciska M.G.

AU - Gauvain, Jean-Luc

AU - den Hartog, Jurgen

AU - den Hartog, Jeremy

AU - Netter, Klaus

N1 - Conference code: 1

PY - 1999/10

Y1 - 1999/10

N2 - This paper describes the Olive project which aims to support automated indexing of video material by use of human language technologies. Olive is making use of speech recognition to automatically derive transcriptions of the sound tracks, generating time-coded linguistic elements which serve as the basis for text-based retrieval functionality. The retrieval demonstrator builds on and extends the architecture from the Pop-Eye project, a system applying human language technology on subtitles for the disclosure of video fragments.

AB - This paper describes the Olive project which aims to support automated indexing of video material by use of human language technologies. Olive is making use of speech recognition to automatically derive transcriptions of the sound tracks, generating time-coded linguistic elements which serve as the basis for text-based retrieval functionality. The retrieval demonstrator builds on and extends the architecture from the Pop-Eye project, a system applying human language technology on subtitles for the disclosure of video fragments.

KW - IR-80669

KW - HMI-MR: MULTIMEDIA RETRIEVAL

KW - EWI-9258

KW - METIS-119718

M3 - Conference contribution

SN - not assigned

SP - 75

EP - 80

BT - Proceedings of the 1st European Workshop on Content-Based Multimedia Indexing (CBMI'99)

PB - IRIT

CY - Toulouse

T2 - 1st European Workshop on Content-Based Multimedia Indexing, CBMI 1999

Y2 - 25 October 1999 through 27 October 1999

ER -