Discriminating capabilities of syllable-based features and approaches of utilizing them for voice retrieval of speech information in Mandarin Chinese

Berlin Chen, Hsin Min Wang, Lin Shan Lee

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

With the rapidly growing use of the audio and multimedia information over the Internet, the technology for retrieving speech information using voice queries is becoming more and more important. In this paper, considering the monosyllabic structure of the Chinese language, a whole class of syllable-based indexing features, including overlapping segments of syllables and Syllable pairs separated by a few syllables, is extensively investigated based on a Mandarin broadcast news database. The strong discriminating capabilities of such syllable-based features were verified by comparing with the word- or character-based features. Good approaches for better utilizing such capabilities, including fusion with the word- and character-level information and improved approaches to obtain better syllable-based features and query expressions, were extensively investigated. Very encouraging experimental results were obtained.

Original languageEnglish
Pages (from-to)303-314
Number of pages12
JournalIEEE Transactions on Speech and Audio Processing
Volume10
Issue number5
DOIs
Publication statusPublished - 2002 Jul 1

Fingerprint

syllables
retrieval
Fusion reactions
Internet
news
multimedia
fusion

Keywords

  • Confidence measure
  • Retrieval of speech information
  • Syllable-based features
  • Term association matrix

ASJC Scopus subject areas

  • Software
  • Acoustics and Ultrasonics
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

@article{1fcc69bb28dd411fa1d431282c586fdd,
title = "Discriminating capabilities of syllable-based features and approaches of utilizing them for voice retrieval of speech information in Mandarin Chinese",
abstract = "With the rapidly growing use of the audio and multimedia information over the Internet, the technology for retrieving speech information using voice queries is becoming more and more important. In this paper, considering the monosyllabic structure of the Chinese language, a whole class of syllable-based indexing features, including overlapping segments of syllables and Syllable pairs separated by a few syllables, is extensively investigated based on a Mandarin broadcast news database. The strong discriminating capabilities of such syllable-based features were verified by comparing with the word- or character-based features. Good approaches for better utilizing such capabilities, including fusion with the word- and character-level information and improved approaches to obtain better syllable-based features and query expressions, were extensively investigated. Very encouraging experimental results were obtained.",
keywords = "Confidence measure, Retrieval of speech information, Syllable-based features, Term association matrix",
author = "Berlin Chen and Wang, {Hsin Min} and Lee, {Lin Shan}",
year = "2002",
month = "7",
day = "1",
doi = "10.1109/TSA.2002.802541",
language = "English",
volume = "10",
pages = "303--314",
journal = "IEEE Transactions on Audio, Speech and Language Processing",
issn = "1558-7916",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Discriminating capabilities of syllable-based features and approaches of utilizing them for voice retrieval of speech information in Mandarin Chinese

AU - Chen, Berlin

AU - Wang, Hsin Min

AU - Lee, Lin Shan

PY - 2002/7/1

Y1 - 2002/7/1

N2 - With the rapidly growing use of the audio and multimedia information over the Internet, the technology for retrieving speech information using voice queries is becoming more and more important. In this paper, considering the monosyllabic structure of the Chinese language, a whole class of syllable-based indexing features, including overlapping segments of syllables and Syllable pairs separated by a few syllables, is extensively investigated based on a Mandarin broadcast news database. The strong discriminating capabilities of such syllable-based features were verified by comparing with the word- or character-based features. Good approaches for better utilizing such capabilities, including fusion with the word- and character-level information and improved approaches to obtain better syllable-based features and query expressions, were extensively investigated. Very encouraging experimental results were obtained.

AB - With the rapidly growing use of the audio and multimedia information over the Internet, the technology for retrieving speech information using voice queries is becoming more and more important. In this paper, considering the monosyllabic structure of the Chinese language, a whole class of syllable-based indexing features, including overlapping segments of syllables and Syllable pairs separated by a few syllables, is extensively investigated based on a Mandarin broadcast news database. The strong discriminating capabilities of such syllable-based features were verified by comparing with the word- or character-based features. Good approaches for better utilizing such capabilities, including fusion with the word- and character-level information and improved approaches to obtain better syllable-based features and query expressions, were extensively investigated. Very encouraging experimental results were obtained.

KW - Confidence measure

KW - Retrieval of speech information

KW - Syllable-based features

KW - Term association matrix

UR - http://www.scopus.com/inward/record.url?scp=0036649836&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036649836&partnerID=8YFLogxK

U2 - 10.1109/TSA.2002.802541

DO - 10.1109/TSA.2002.802541

M3 - Article

AN - SCOPUS:0036649836

VL - 10

SP - 303

EP - 314

JO - IEEE Transactions on Audio, Speech and Language Processing

JF - IEEE Transactions on Audio, Speech and Language Processing

SN - 1558-7916

IS - 5

ER -