Corpus ID: 15687798

Improvement in corpus-based generation of F0 contours using generation process model for emotional speech synthesis

@inproceedings{Hirose2004ImprovementIC,
  title={Improvement in corpus-based generation of F0 contours using generation process model for emotional speech synthesis},
  author={K. Hirose},
  booktitle={INTERSPEECH},
  year={2004}
}
  • K. Hirose
  • Published in INTERSPEECH 2004
  • Computer Science
  • A corpus-based method was developed for generating fundamental frequency contours in emotional speech synthesis. The method assumes the generation process model and predicts its command parameters (positions and amplitudes) using binary regression trees with the input of linguistic information of the sentence to be synthesized. Because of the model constraint, a certain quality is still kept in synthesized speech even if the prediction is done incorrectly. The speech corpus includes three types… CONTINUE READING
    8 Citations
    Control of prosodie focus in corpus-based generation of fundamental frequency contours based on the generation process model
    • PDF
    Exemplar-based pitch contour generation using DOP for syntactic tree decomposition
    • 2
    • PDF
    Evaluation of Expressive Speech Synthesis With Voice Conversion and Copy Resynthesis Techniques
    • O. Türk, M. Schröder
    • Computer Science
    • IEEE Transactions on Audio, Speech, and Language Processing
    • 2010
    • 57

    References

    SHOWING 1-10 OF 17 REFERENCES
    Corpus-based synthesis of fundamental frequency contours based on a generation process model
    • 11
    • PDF
    Data-driven generation of F0 contours using a superpositional model
    • 39
    A corpus-based speech synthesis system with emotion
    • 154
    Analysis of voice fundamental frequency contours for declarative sentences of Japanese
    • 481
    • PDF
    A method for automatic extraction of model parameters from fundamental frequency contours of speech
    • 83
    • PDF
    Modeling of various speaking styles and emotions for HMM-based speech synthesis
    • 72
    • PDF
    Japanese Syntactic Analysis System KNP http://www-nagao.kuee.kyoto-u.ac.jp/projects/nl- resource
    • Japanese Syntactic Analysis System KNP http://www-nagao.kuee.kyoto-u.ac.jp/projects/nl- resource
    A study on emotional speech synthesis based on HMM
    • Record of Fall Meeting Acoust. Soc. Japan
    • 2003