Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition

Research output: Book/ReportReportProfessional

22 Downloads (Pure)

Abstract

This paper reports on the setup and evaluation of robust speech recognition system parts, geared towards transcript generation for heterogeneous, real-life media collections. The system is deployed for generating speech transcripts for the NIST/TRECVID-2007 test collection, part of a Dutch real-life archive of news-related genres. Performance figures for this type of content are compared to figures for broadcast news test data.
Original languageUndefined
Place of PublicationEnschede
PublisherCentre for Telematics and Information Technology (CTIT)
Number of pages11
Publication statusPublished - 9 May 2007

Publication series

NameCTIT Technical Report Series
PublisherUniversity of Twente, Centre for Telematics and Information Technology (CTIT)
No.WP07-01/TR-CTIT-07-30
ISSN (Print)1381-3625

Keywords

  • HMI-SLT: Speech and Language Technology
  • EWI-9783
  • Information Retrieval
  • Automatic Speech Recognition
  • IR-95701
  • METIS-241618
  • HMI-MR: MULTIMEDIA RETRIEVAL

Cite this

Huijbregts, M. A. H., Ordelman, R. J. F., & de Jong, F. M. G. (2007). Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition. (CTIT Technical Report Series; No. WP07-01/TR-CTIT-07-30). Enschede: Centre for Telematics and Information Technology (CTIT).
Huijbregts, M.A.H. ; Ordelman, Roeland J.F. ; de Jong, Franciska M.G. / Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition. Enschede : Centre for Telematics and Information Technology (CTIT), 2007. 11 p. (CTIT Technical Report Series; WP07-01/TR-CTIT-07-30).
@book{7b27046ff9254ab38d6cf614d36c145b,
title = "Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition",
abstract = "This paper reports on the setup and evaluation of robust speech recognition system parts, geared towards transcript generation for heterogeneous, real-life media collections. The system is deployed for generating speech transcripts for the NIST/TRECVID-2007 test collection, part of a Dutch real-life archive of news-related genres. Performance figures for this type of content are compared to figures for broadcast news test data.",
keywords = "HMI-SLT: Speech and Language Technology, EWI-9783, Information Retrieval, Automatic Speech Recognition, IR-95701, METIS-241618, HMI-MR: MULTIMEDIA RETRIEVAL",
author = "M.A.H. Huijbregts and Ordelman, {Roeland J.F.} and {de Jong}, {Franciska M.G.}",
note = "http://eprints.ewi.utwente.nl/9783",
year = "2007",
month = "5",
day = "9",
language = "Undefined",
series = "CTIT Technical Report Series",
publisher = "Centre for Telematics and Information Technology (CTIT)",
number = "WP07-01/TR-CTIT-07-30",
address = "Netherlands",

}

Huijbregts, MAH, Ordelman, RJF & de Jong, FMG 2007, Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition. CTIT Technical Report Series, no. WP07-01/TR-CTIT-07-30, Centre for Telematics and Information Technology (CTIT), Enschede.

Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition. / Huijbregts, M.A.H.; Ordelman, Roeland J.F.; de Jong, Franciska M.G.

Enschede : Centre for Telematics and Information Technology (CTIT), 2007. 11 p. (CTIT Technical Report Series; No. WP07-01/TR-CTIT-07-30).

Research output: Book/ReportReportProfessional

TY - BOOK

T1 - Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition

AU - Huijbregts, M.A.H.

AU - Ordelman, Roeland J.F.

AU - de Jong, Franciska M.G.

N1 - http://eprints.ewi.utwente.nl/9783

PY - 2007/5/9

Y1 - 2007/5/9

N2 - This paper reports on the setup and evaluation of robust speech recognition system parts, geared towards transcript generation for heterogeneous, real-life media collections. The system is deployed for generating speech transcripts for the NIST/TRECVID-2007 test collection, part of a Dutch real-life archive of news-related genres. Performance figures for this type of content are compared to figures for broadcast news test data.

AB - This paper reports on the setup and evaluation of robust speech recognition system parts, geared towards transcript generation for heterogeneous, real-life media collections. The system is deployed for generating speech transcripts for the NIST/TRECVID-2007 test collection, part of a Dutch real-life archive of news-related genres. Performance figures for this type of content are compared to figures for broadcast news test data.

KW - HMI-SLT: Speech and Language Technology

KW - EWI-9783

KW - Information Retrieval

KW - Automatic Speech Recognition

KW - IR-95701

KW - METIS-241618

KW - HMI-MR: MULTIMEDIA RETRIEVAL

M3 - Report

T3 - CTIT Technical Report Series

BT - Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition

PB - Centre for Telematics and Information Technology (CTIT)

CY - Enschede

ER -

Huijbregts MAH, Ordelman RJF, de Jong FMG. Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition. Enschede: Centre for Telematics and Information Technology (CTIT), 2007. 11 p. (CTIT Technical Report Series; WP07-01/TR-CTIT-07-30).