Cepstrum-based pitch detection using a new statistical V/UV classification algorithm

Sassan Ahmadi, Andreas Spanias

Research output: Contribution to journalArticle

128 Citations (Scopus)

Abstract

An improved cepstrum-based voicing detection and pitch determination algorithm is presented. Voicing decisions are made using a multifeature voiced/unvoiced classification algorithm based on statistical analysis of cepstral peak, zero-crossing rate, and energy of short-time segments of the speech signal. Pitch frequency information is extracted by a modified cepstrum-based method and then carefully refined using pitch tracking, correction, and smoothing algorithms. Performance analysis on a large database indicates considerable improvement relative to the conventional cepstrum method. The proposed algorithm is also shown to be robust to additive noise.

Original languageEnglish (US)
Pages (from-to)333-338
Number of pages6
JournalIEEE Transactions on Speech and Audio Processing
Volume7
Issue number3
DOIs
StatePublished - 1999
Externally publishedYes

Fingerprint

roots of equations
Additive noise
smoothing
statistical analysis
Statistical methods
energy

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Cepstrum-based pitch detection using a new statistical V/UV classification algorithm. / Ahmadi, Sassan; Spanias, Andreas.

In: IEEE Transactions on Speech and Audio Processing, Vol. 7, No. 3, 1999, p. 333-338.

Research output: Contribution to journalArticle

@article{6d895f68adf644d69370d9632b62dcba,
title = "Cepstrum-based pitch detection using a new statistical V/UV classification algorithm",
abstract = "An improved cepstrum-based voicing detection and pitch determination algorithm is presented. Voicing decisions are made using a multifeature voiced/unvoiced classification algorithm based on statistical analysis of cepstral peak, zero-crossing rate, and energy of short-time segments of the speech signal. Pitch frequency information is extracted by a modified cepstrum-based method and then carefully refined using pitch tracking, correction, and smoothing algorithms. Performance analysis on a large database indicates considerable improvement relative to the conventional cepstrum method. The proposed algorithm is also shown to be robust to additive noise.",
author = "Sassan Ahmadi and Andreas Spanias",
year = "1999",
doi = "10.1109/89.759042",
language = "English (US)",
volume = "7",
pages = "333--338",
journal = "IEEE Transactions on Speech and Audio Processing",
issn = "1558-7916",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Cepstrum-based pitch detection using a new statistical V/UV classification algorithm

AU - Ahmadi, Sassan

AU - Spanias, Andreas

PY - 1999

Y1 - 1999

N2 - An improved cepstrum-based voicing detection and pitch determination algorithm is presented. Voicing decisions are made using a multifeature voiced/unvoiced classification algorithm based on statistical analysis of cepstral peak, zero-crossing rate, and energy of short-time segments of the speech signal. Pitch frequency information is extracted by a modified cepstrum-based method and then carefully refined using pitch tracking, correction, and smoothing algorithms. Performance analysis on a large database indicates considerable improvement relative to the conventional cepstrum method. The proposed algorithm is also shown to be robust to additive noise.

AB - An improved cepstrum-based voicing detection and pitch determination algorithm is presented. Voicing decisions are made using a multifeature voiced/unvoiced classification algorithm based on statistical analysis of cepstral peak, zero-crossing rate, and energy of short-time segments of the speech signal. Pitch frequency information is extracted by a modified cepstrum-based method and then carefully refined using pitch tracking, correction, and smoothing algorithms. Performance analysis on a large database indicates considerable improvement relative to the conventional cepstrum method. The proposed algorithm is also shown to be robust to additive noise.

UR - http://www.scopus.com/inward/record.url?scp=0032654850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032654850&partnerID=8YFLogxK

U2 - 10.1109/89.759042

DO - 10.1109/89.759042

M3 - Article

AN - SCOPUS:0032654850

VL - 7

SP - 333

EP - 338

JO - IEEE Transactions on Speech and Audio Processing

JF - IEEE Transactions on Speech and Audio Processing

SN - 1558-7916

IS - 3

ER -