Evaluating the quality of an integrated model of German prosody

International Journal of Speech Technology

Volumn 6, Issue 1, 2003, Pages 45-55

  Mixdorff, Hansjörg ^a,b   Jokisch, Oliver ^b  

^a SRH Berlin University of Applied Sciences   (Germany)

^b DRESDEN UNIVERSITY OF TECHNOLOGY   (Germany)

Author keywords

Evaluation of prosodic quality; Fujisaki model; Prosody in text to speech

Indexed keywords

INFORMATION ANALYSIS; INTEGRATION; MATHEMATICAL MODELS; PARAMETER ESTIMATION; STATISTICAL METHODS;

INTEGRATED MODELS;

SPEECH SYNTHESIS;

EID: 0037235173     PISSN: 13812416     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1021099922328     Document Type: Article

References (15)

1. Corrigan, G., Massey, N., and Karaaly, O. (1997). Generating segment durations in a text-to-speech system: A hybrid rule-based/neural network approach. Proc. Eurospeech'97. Rhodes, vol. 5, pp. 2675-2678.
2. Fujisaki, H. and Hirose, K. (1984). Analysis of voice fundamental frequency contours for declarative sentences of Japanese. Journal of the Acoustical Society of Japan (E), 5(4):233-241.
3. Hecht-Nielsen, R. (1990). Neurocomputing. Reading (Mass.): Addison-Wesley.
4. Hoffmann, R. (1999/II). A multilingual text-to-speech system. The Phonetician, 80:5-10.
5. Jokisch, O., Hirschfeld, D., Eichner, M., and Hoffmann, R. (1998). Multi-level rhythm control for speech synthesis using hybrid data driven and role-based approaches. Proceedings of ICSLP'98. Sydney, pp. 607-610.
6. Jokisch, O., Mixdorff, H. et al. (2000). Learning the parameters of quantitative prosody models. Proceedings ICSLP 2000. Beijing, China, vol. 1, pp. 645-648.
7. Mixdorff, H. (1998). Intonation Patterns of German-Model-based. Quantitative Analysis and Synthesis of F0-Contours. PhD thesis TU Dresden (http://www.tfh-berlin.de/̃mixdorff/thesis.htm).
8. Mixdorff, H. (2000). A novel approach to the fully automatic extraction of Fujisaki model parameters. Proceedings ICASSP 2000. Istanbul, Turkey, vol. 3, pp. 1281-1284.
9. Mixdorff, H. and Jokisch, O. (2001a). Building au integrated prosodic model of German. Proceedings of Eurospeech 2001. Aalborg, Denmark, vol. 2, pp. 947-950.
10. Mixdorff, H. and Jokisch, O. (2001b). Comparing a data-driven and a rule-based approach to predicting prosodic features of German. Tagungsband der 12. Konferenz Elektronische Sprachsignalverarbeitung. Bonn, Germany, pp. 298-305.
11. Mixdorff, H. and Mehnert, D. (1999). Exploring the naturalness of several German high-quality-text-to-speech systems. Proceedings of Eurospeech '99. Budapest, Hungary, vol. 4, pp. 1859-1862.
12. Rapp, S. (1998). Automatisierte Erstellung von Korpora für die Prosodieforschung. PhD thesis Universität Stuttgart, Institut für Maschinelle Sprachverarbeitung.
13. Sonntag, G.P. and Portele, T. (1998). PURR-a method for prosody evaluation and investigation. Journal of Computer Speech and Language, 12(4):437-451. Special issue on evaluation in language and speech technology.
14. Stöber, K., Portele, T., Wagner, P., and Hess, W. (1999). Synthesis by word concatenation. Proceedings of EUROSPEECH '99. Budapest, vol. 2, pp. 619-622.
15. Zell, A. (1994). Simulation Neuronaler Netze, Bonn, Addison-Wesley.