Discrimination Method of Synthetic Speech Using Pitch Frequency against Synthetic Speech Falsification

Akio OGIHARA; Hitoshi UNNO; Akira SHIOZAKI

doi:10.1093/ietfec/e88-a.1.280

Discrimination Method of Synthetic Speech Using Pitch Frequency against Synthetic Speech Falsification

Akio OGIHARA, Hitoshi UNNO, Akira SHIOZAKI

Full Text Views

0

Share
Cite this

Summary :

We propose discrimination method of synthetic speech using pitch pattern of speech signal. By applying the proposed synthetic speech discrimination system as pre-process before the conventional HMM speaker verification system, we can improve the safety of conventional speaker verification system against imposture using synthetic speech. The proposed method distinguishes between synthetic speech and natural speech according to the pitch pattern which is distribution of value of normalized short-range autocorrelation function. We performed the experiment of user verification, and confirmed the validity of the proposed method.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E88-A No.1 pp.280-286

Publication Date: 2005/01/01

Publicized

Online ISSN

DOI: 10.1093/ietfec/e88-a.1.280

Type of Manuscript: Special Section PAPER (Special Section on Cryptography and Information Security)

Category: Biometrics

Cite this

Copy

Akio OGIHARA, Hitoshi UNNO, Akira SHIOZAKI, "Discrimination Method of Synthetic Speech Using Pitch Frequency against Synthetic Speech Falsification" in IEICE TRANSACTIONS on Fundamentals, vol. E88-A, no. 1, pp. 280-286, January 2005, doi: 10.1093/ietfec/e88-a.1.280.
Abstract: We propose discrimination method of synthetic speech using pitch pattern of speech signal. By applying the proposed synthetic speech discrimination system as pre-process before the conventional HMM speaker verification system, we can improve the safety of conventional speaker verification system against imposture using synthetic speech. The proposed method distinguishes between synthetic speech and natural speech according to the pitch pattern which is distribution of value of normalized short-range autocorrelation function. We performed the experiment of user verification, and confirmed the validity of the proposed method.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e88-a.1.280/_p

Copy

@ARTICLE{e88-a_1_280,
author={Akio OGIHARA, Hitoshi UNNO, Akira SHIOZAKI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Discrimination Method of Synthetic Speech Using Pitch Frequency against Synthetic Speech Falsification},
year={2005},
volume={E88-A},
number={1},
pages={280-286},
abstract={We propose discrimination method of synthetic speech using pitch pattern of speech signal. By applying the proposed synthetic speech discrimination system as pre-process before the conventional HMM speaker verification system, we can improve the safety of conventional speaker verification system against imposture using synthetic speech. The proposed method distinguishes between synthetic speech and natural speech according to the pitch pattern which is distribution of value of normalized short-range autocorrelation function. We performed the experiment of user verification, and confirmed the validity of the proposed method.},
keywords={},
doi={10.1093/ietfec/e88-a.1.280},
ISSN={},
month={January},}

Copy

TY - JOUR
TI - Discrimination Method of Synthetic Speech Using Pitch Frequency against Synthetic Speech Falsification
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 280
EP - 286
AU - Akio OGIHARA
AU - Hitoshi UNNO
AU - Akira SHIOZAKI
PY - 2005
DO - 10.1093/ietfec/e88-a.1.280
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E88-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2005
AB - We propose discrimination method of synthetic speech using pitch pattern of speech signal. By applying the proposed synthetic speech discrimination system as pre-process before the conventional HMM speaker verification system, we can improve the safety of conventional speaker verification system against imposture using synthetic speech. The proposed method distinguishes between synthetic speech and natural speech according to the pitch pattern which is distribution of value of normalized short-range autocorrelation function. We performed the experiment of user verification, and confirmed the validity of the proposed method.
ER -