Learning the parameters of quantitative prosody models

6th International Conference on Spoken Language Processing, ICSLP 2000

Volumn , Issue , 2000, Pages

  Jokisch, Oliver ^a   Mixdorff, Hansjörg ^a   Kruschke, Hans ^a   Kordon, Ulrich ^a  

^a DRESDEN UNIVERSITY OF TECHNOLOGY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

COMPLEX NETWORKS; EXTRACTION;

AUTOMATIC EXTRACTION; FLEXIBLE TRAININGS; HYBRID NEURAL NETWORKS; INTONATION MODELING; NEURAL NETWORK (NN); QUANTITATIVE MODELING; QUANTITATIVE MODELS; RULE-BASED APPROACH;

SPEECH RECOGNITION;

EID: 85009010962     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. Mixdorff, H.: Intonation patterns of German - Quantitative analysis and synthesis of F0 contours. Ph. D. Thesis, TU Dresden, Dresden, 1998.
2. G. Sonntag et al: Comparative evaluation of six German TTS systems. Proc. Eurospeech'99, Budapest, Vol. 1, 251-254.
3. C. Traber: F0 generation with a database of natural f0 patterns and with a neural network. In G. Bailly, ed.: Talking Machines: Theories, Models and Designs, 287-304, North Holland, 1992.
4. R. Hoffmann et al: Evaluation of a multilingual TTS system with respect to the prosodic quality. Proc. ICPhS'99, San Francisco, 2307-2310
5. O. Jokisch et al: Multi-level rhythm control for speech synthesis using hybrid data driven and rule-based approaches. Proc. ICSLP'98, Sydney, 607-610.
6. th German Conference on Acoustics), Zurich, 352-353.
7. Rapp, S.: Automatisierte Erstellung von Korpora für die Prosodieforschung. Ph. D. Thesis, University of Stuttgart, Stuttgart, 1998.
8. Mayer, J.: sTranscription of German intonation: The Stuttgart system. Technical report, University of Stuttgart; Stuttgart, 1995.
9. Mixdorff, H.: A novel approach to the to fully automatic extraction of Fujisaki model parameters. Proc. ICASSP 2000, Istanbul, Vol. 3, 1281-1284