Voice retrieval of Mandarin broadcast news speech

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper presents an improved framework for voice retrieval of Mandarin broadcast news speech. First, several unsupervised and data-driven approaches for broadcast news transcription were proposed to improve the speech recognition accuracy and efficiency. Then, a multiscale indexing paradigm for broadcast news retrieval was exploited to alleviate the problems caused by the speech recognition errors and the flexible wording structure of the Chinese language. Finally, we used the PDA as the platform and broadcast radio programs collected in Taiwan as the document collection to establish a speech-based multimedia information retrieval prototype system. Very encouraging results were obtained.

Original languageEnglish
Pages (from-to)91-109
Number of pages19
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume20
Issue number1
DOIs
Publication statusPublished - 2006 Feb 1

Fingerprint

Speech recognition
Information retrieval systems
Flexible structures
Personal digital assistants
Transcription

Keywords

  • Broadcast news
  • Information retrieval
  • Multimedia
  • Multiscale indexing
  • Speech recognition

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Voice retrieval of Mandarin broadcast news speech. / Chen, Berlin.

In: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 20, No. 1, 01.02.2006, p. 91-109.

Research output: Contribution to journalArticle

@article{140bf4dd95084894bc71effe49005327,
title = "Voice retrieval of Mandarin broadcast news speech",
abstract = "This paper presents an improved framework for voice retrieval of Mandarin broadcast news speech. First, several unsupervised and data-driven approaches for broadcast news transcription were proposed to improve the speech recognition accuracy and efficiency. Then, a multiscale indexing paradigm for broadcast news retrieval was exploited to alleviate the problems caused by the speech recognition errors and the flexible wording structure of the Chinese language. Finally, we used the PDA as the platform and broadcast radio programs collected in Taiwan as the document collection to establish a speech-based multimedia information retrieval prototype system. Very encouraging results were obtained.",
keywords = "Broadcast news, Information retrieval, Multimedia, Multiscale indexing, Speech recognition",
author = "Berlin Chen",
year = "2006",
month = "2",
day = "1",
doi = "10.1142/S0218001406004521",
language = "English",
volume = "20",
pages = "91--109",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "1",

}

TY - JOUR

T1 - Voice retrieval of Mandarin broadcast news speech

AU - Chen, Berlin

PY - 2006/2/1

Y1 - 2006/2/1

N2 - This paper presents an improved framework for voice retrieval of Mandarin broadcast news speech. First, several unsupervised and data-driven approaches for broadcast news transcription were proposed to improve the speech recognition accuracy and efficiency. Then, a multiscale indexing paradigm for broadcast news retrieval was exploited to alleviate the problems caused by the speech recognition errors and the flexible wording structure of the Chinese language. Finally, we used the PDA as the platform and broadcast radio programs collected in Taiwan as the document collection to establish a speech-based multimedia information retrieval prototype system. Very encouraging results were obtained.

AB - This paper presents an improved framework for voice retrieval of Mandarin broadcast news speech. First, several unsupervised and data-driven approaches for broadcast news transcription were proposed to improve the speech recognition accuracy and efficiency. Then, a multiscale indexing paradigm for broadcast news retrieval was exploited to alleviate the problems caused by the speech recognition errors and the flexible wording structure of the Chinese language. Finally, we used the PDA as the platform and broadcast radio programs collected in Taiwan as the document collection to establish a speech-based multimedia information retrieval prototype system. Very encouraging results were obtained.

KW - Broadcast news

KW - Information retrieval

KW - Multimedia

KW - Multiscale indexing

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=33644999048&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33644999048&partnerID=8YFLogxK

U2 - 10.1142/S0218001406004521

DO - 10.1142/S0218001406004521

M3 - Article

AN - SCOPUS:33644999048

VL - 20

SP - 91

EP - 109

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 1

ER -