Vronis, J., Di Cristo, P., Courtois, F. & Lagrue, B. 1997. A stochastic model of intonation for text-to-speech synthesis. Proceedings Eurospeech '97 (Rhodes) 5: 2643-2646. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Automatic Stylisation and Symbolic Coding of F 0 .. - Campione, Hirst, Veronis (Correct)
....from a slight distortion due to the lack of microprosodic effects in the stylised curves, the corrected versions were considered by the experts perceptually identical to the original recordings. Two different methods (qualitative and quantitative) were used to analyse the results (Campione and Vronis, 1998a and b) 0.6.1.4 Statistical analysis We first studied the characteristics of the distribution of target points as well as the intervals between successive target points for the French and Italian corpora (see a detailed analysis in Campione and Vronis, 1998c) The corpus analysed provided 6329 ....
....to analyse the results (Campione and Vronis, 1998a and b) 0.6.1. 4 Statistical analysis We first studied the characteristics of the distribution of target points as well as the intervals between successive target points for the French and Italian corpora (see a detailed analysis in Campione and Vronis, 1998c) The corpus analysed provided 6329 target points for French and 9804 for Italian. The fundamental frequency of the target points was converted to semi tones (STs) The standard deviation varied from 2.79 to 4.18 STs for the French speakers and from 2.78 to 4.44 STs for the Italian speakers. The ....
Vronis, J., DiCristo, P., Courtois, F., Chaumette, C. 1998. A stochastic model of intonation for Text-to-Speech Synthesis, Speech Communication, forthcoming.
The Symbolic Coding Of Segmental Duration And Tonal Alignment: An.. - Hirst (1999) (Correct)
.... with MOMEL, which provides an automatic stylisation of F0 curves [12] 13] INTSINT has been used as a reversible coding system for F0 curves for a number of languages [1] 15] 21] and the representation system developed has now been implemented in two text to speech systems for French [4] [22], In the rest of this paper, rather than the iconic symbols used in (1) I use the orthographic symbols (T, M, B etc. which (with the exception of D and L) have been integrated into the SAM phonetic alphabet SAMPA[23] This alphabet is particularly suitable for computer coding since it makes use ....
Vronis, J., Di Cristo, P., Courtois, F. & Lagrue, B. 1997. A stochastic model of intonation for text-to-speech synthesis. Proceedings Eurospeech '97 (Rhodes) 5: 2643-2646.
ProZed: A Multilingual Prosody Editor for Speech Synthesis - Hirst (2000) (Correct)
No context found.
Vronis, J., Di Cristo, P., Courtois, F. & Lagrue, B. 1997. A stochastic model of intonation for text-to-speech synthesis. Proceedings Eurospeech '97 (Rhodes) 5: 2643-2646.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC