1994
DOI: 10.1121/1.409071
|View full text |Cite
|
Sign up to set email alerts
|

Effect of speaking style on parameters of fundamental frequency contour

Abstract: The authors have analyzed the fundamental frequency (F0) contours of Japanese sentences spoken in four styles, e.g., normal, hurried, angry, and kind, for the synthesis of natural sounding speech. Thirty-five sentences in each speaking style spoken by a professional narrator were analyzed. The parameters of the F0 generation model proposed by Fujisaki, e.g., the minimum value of F0 (Fmin), the amplitude of the phrase commands (Ap) and the amplitude of the accent commands (Aa), are used here as key factors in t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
5
0
2

Year Published

1996
1996
2024
2024

Publication Types

Select...
4
2
2

Relationship

1
7

Authors

Journals

citations
Cited by 15 publications
(7 citation statements)
references
References 6 publications
0
5
0
2
Order By: Relevance
“…São também características prosódicas que distinguem os estilos estudados por Higuchi et al (1997) em japonês, a saber, enunciados naturais atuados com raiva, gentileza e de forma apressada. Os autores apontaram que o valor mínimo da frequência fundamental (F 0 ) se manteve alto para a raiva com contornos melódicos monótonos.…”
Section: Considerações Finaisunclassified
“…São também características prosódicas que distinguem os estilos estudados por Higuchi et al (1997) em japonês, a saber, enunciados naturais atuados com raiva, gentileza e de forma apressada. Os autores apontaram que o valor mínimo da frequência fundamental (F 0 ) se manteve alto para a raiva com contornos melódicos monótonos.…”
Section: Considerações Finaisunclassified
“…Studies relating to intonation and emotions that use this parameter (pitch level) to analyze the relationship between these two variables are highly numerous. 2,12,13 These studies have found that pitch level is quite significant when determining the type of emotion that is conveyed. In a study applied to radio news, the selection of an inadequate pitch level entailed a greater error in intonation for the sample.…”
Section: Introductionmentioning
confidence: 98%
“…This speech is then compared with read speech, with the same speaker reading an edited transcript of the earlier spontaneous speech. Higuchi et al (1997) used the Fujisaki model of intonation to implement speaking styles for text-to-speech synthesis (hence TTS). They measured parameters of the model for four speaking styles, and derived rules for style conversion.…”
Section: Introductionmentioning
confidence: 99%