1992
DOI: 10.1016/0167-6393(92)90010-5
|View full text |Cite
|
Sign up to set email alerts
|

Synthesis: Modeling variability and constraints

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0
1

Year Published

1992
1992
2014
2014

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 12 publications
(7 citation statements)
references
References 36 publications
0
6
0
1
Order By: Relevance
“…Previous attempts to systematically vary acoustic parameters experienced technical constraints with regard to natural sound quality (Carlson, 1992;Frick, 1985;Kappas, Hess, & Scherer, 1991), especially for the manipulation of F0 variation (Brown et al, 1973). Previous studies that investigated the contribution of F0 and amplitude on listeners' judgements of synthesised tone stimuli, in which acoustic information was systematically manipulated, demonstrated that mean F0, F0 variation, and tempo were the most powerful cues for listeners' judgements (Lieberman & Michaels, 1962;Scherer & Oshinsky, 1977).…”
Section: Acoustic Correlates Of Vocal Emotionsmentioning
confidence: 96%
“…Previous attempts to systematically vary acoustic parameters experienced technical constraints with regard to natural sound quality (Carlson, 1992;Frick, 1985;Kappas, Hess, & Scherer, 1991), especially for the manipulation of F0 variation (Brown et al, 1973). Previous studies that investigated the contribution of F0 and amplitude on listeners' judgements of synthesised tone stimuli, in which acoustic information was systematically manipulated, demonstrated that mean F0, F0 variation, and tempo were the most powerful cues for listeners' judgements (Lieberman & Michaels, 1962;Scherer & Oshinsky, 1977).…”
Section: Acoustic Correlates Of Vocal Emotionsmentioning
confidence: 96%
“…(1987), et même des caractéristiques individuelles du locuteur, cf. Carlson (1992). Ces différents aspects qui visent tous à améliorer l'intelligibilité et le naturel des systèmes de synthèse, et en définitive à en favoriser l'acceptabilité dans une multi tude de situations dans la mesure où leur output se rapproche encore plus du langage humain, mettent tous en cause sous une forme ou l'autre la variabilité linguistique.…”
Section: Problématiqueunclassified
“…It is apparent, however, that emotion is conveyed by changes in pitch, timing and voice quality, which occur in different combinations for different emotions. Using current knowledge of emotions in human speech (Murray & Arnott, 1995), some prototype synthetic speech-with-emotion systems, including HAMLET, have been developed using existing synthesisers based on formant (Murray and Arnott, 1993, Cahn, 1990, Lewis & Tatham, 1995, Carlson, 1992 and concatenative technology (Murray and Edgington, 1998) . A review of progress and future possibilities in this area is given in (Murray et al, 1996).…”
Section: Emotion In Speech Synthesismentioning
confidence: 99%