Loading...
Please wait, while we are loading the content...
Similar Documents
Realization of prosodic focuses in corpus-based generation of fundamental frequency contours of japanese based on the generation process model.
| Content Provider | CiteSeerX |
|---|---|
| Author | Ochi, Keiko Hirose, Keikichi Minematsu, Nobuaki |
| Abstract | A method was developed for generating sentence F 0 contours of Japanese, when a focus is placed in one of the “bunsetsu ” of an utterance. It controls F 0 based on the F 0 model; not frame-byframe F 0 prediction as in the case of HMM-based speech synthesis. The method first predicts differences in the F 0 model commands between utterances with and without focus, and then applies them to the F 0 model commands predicted beforehand by the baseline method without focus assignment. The baseline method is trained using a large corpus, while corpus for training command differences can be small and not necessarily be uttered by the same speaker of the large corpus. The validity of the method was proved by the experiment on F 0 contour generation and speech synthesis, including interpolation/extrapolation of the F 0 model commands for focus level control. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Model Command Corpus-based Generation Generation Process Model Prosodic Focus Fundamental Frequency Contour Large Corpus Baseline Method Hmm-based Speech Synthesis Focus Assignment Speech Synthesis Interpolation Extrapolation Command Difference Focus Level Control Contour Generation |
| Content Type | Text |
