On the prediction of global F0 shape for Japanese text-to-speech

Yoshinori Sagisaka

On the prediction of global F₀ shape for Japanese text-to-speech

Yoshinori Sagisaka^*

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

35 Citations (Scopus)

Abstract

The global F₀ shape of Japanese speech is predicted by phrasal accent attributes and adjacent phrasal environment using three-layered neural nets. Three F₀ values of each minor phrase are used for the global shape description, and their prediction is carried out in each major phrase determined by right-branching syntactic boundaries. Through prediction experiments using short and ordinary sentence samples, it is quantitatively confirmed that the global F₀ shapes are predicted fairly well in both samples and that additional controls are necessary for finer prediction in the ordinary sentence samples.

Original language	English
Pages (from-to)	325-328
Number of pages	4
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	1
Publication status	Published - 1990 Dec 1
Externally published	Yes
Event	1990 International Conference on Acoustics, Speech, and Signal Processing: Speech Processing 2, VLSI, Audio and Electroacoustics Part 2 (of 5) - Albuquerque, New Mexico, USA Duration: 1990 Apr 3 → 1990 Apr 6

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Cite this

@article{cdefe977808a4b458cb1b5683dfd4a28,

title = "On the prediction of global F0 shape for Japanese text-to-speech",

abstract = "The global F0 shape of Japanese speech is predicted by phrasal accent attributes and adjacent phrasal environment using three-layered neural nets. Three F0 values of each minor phrase are used for the global shape description, and their prediction is carried out in each major phrase determined by right-branching syntactic boundaries. Through prediction experiments using short and ordinary sentence samples, it is quantitatively confirmed that the global F0 shapes are predicted fairly well in both samples and that additional controls are necessary for finer prediction in the ordinary sentence samples.",

author = "Yoshinori Sagisaka",

year = "1990",

month = dec,

day = "1",

language = "English",

volume = "1",

pages = "325--328",

journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",

issn = "0736-7791",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "1990 International Conference on Acoustics, Speech, and Signal Processing: Speech Processing 2, VLSI, Audio and Electroacoustics Part 2 (of 5) ; Conference date: 03-04-1990 Through 06-04-1990",

}

TY - JOUR

T1 - On the prediction of global F0 shape for Japanese text-to-speech

AU - Sagisaka, Yoshinori

PY - 1990/12/1

Y1 - 1990/12/1

N2 - The global F0 shape of Japanese speech is predicted by phrasal accent attributes and adjacent phrasal environment using three-layered neural nets. Three F0 values of each minor phrase are used for the global shape description, and their prediction is carried out in each major phrase determined by right-branching syntactic boundaries. Through prediction experiments using short and ordinary sentence samples, it is quantitatively confirmed that the global F0 shapes are predicted fairly well in both samples and that additional controls are necessary for finer prediction in the ordinary sentence samples.

AB - The global F0 shape of Japanese speech is predicted by phrasal accent attributes and adjacent phrasal environment using three-layered neural nets. Three F0 values of each minor phrase are used for the global shape description, and their prediction is carried out in each major phrase determined by right-branching syntactic boundaries. Through prediction experiments using short and ordinary sentence samples, it is quantitatively confirmed that the global F0 shapes are predicted fairly well in both samples and that additional controls are necessary for finer prediction in the ordinary sentence samples.

UR - http://www.scopus.com/inward/record.url?scp=0025671537&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025671537&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0025671537

SN - 0736-7791

VL - 1

SP - 325

EP - 328

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

T2 - 1990 International Conference on Acoustics, Speech, and Signal Processing: Speech Processing 2, VLSI, Audio and Electroacoustics Part 2 (of 5)

Y2 - 3 April 1990 through 6 April 1990

ER -

On the prediction of global F₀ shape for Japanese text-to-speech

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this