Prosody Modelling for Syllable-based Speech Synthesis
ثبت نشده
چکیده
Prosody model used in the syllable based speech synthesizer DEMOSTHENES is described in the paper. The paper focuses on the segmental structure, especially on the segmentation into rhythm units (prosodic phrases). Relations between prosodic segments and sentence constituents are also discussed.
منابع مشابه
Improvements in Prosodic Processing for Speech Synthesis
For the synthesis of French, a separate modelling of fundamental frequency and timing seems more appropriate than derived modelling. Satisfactory declarative prosody in synthesis can be obtained with a version of Fujisaki F0 modelling that takes into account syllable amplitude differences as well as microprosody. Statistical methods based on both segmental and lexical input provide a satisfacto...
متن کاملStylization and Trajectory Modelling of Short and Long Term Speech Prosody Variations
In this paper, a unified trajectory model based on the stylization and the modelling of f0 variations simultaneously over various temporal domains is proposed. The syllable is used as the minimal temporal domain for the description of speech prosody, and short-term and long-term f0 variations are stylized and modelled simultaneously over various temporal domains. During the training, a context-...
متن کاملStatistical Modelling of Speech Segment Duration by Constrained Tree Regression
This paper presents a new method for statistical modelling of prosody control in speech synthesis. The proposed method, which is referred to as Constrained Tree Regression (CTR), can make suitable representation of complex effects of control factors for prosody with a moderate amount of learning data. It is based on recursive splits of predictor variable spaces and partial imposition of constra...
متن کاملAutomatic prominence annotation of a German speech synthesis corpus: towards prominence-based prosody generation for unit selection synthesis
This paper describes work directed towards the development of a syllable prominence-based prosody generation functionality for a German unit selection speech synthesis system. A general concept for syllable prominence-based prosody generation in unit selection synthesis is proposed. As a first step towards its implementation, an automated syllable prominence annotation procedure based on acoust...
متن کاملSyllable based models for prosody modeling in HMM based speech synthesis
Simple4All is a speech synthesis research project that aims to ease the production of synthetic voices in new languages by means of unsupervised modeling techniques. In this work, we introduce syllable based models for prosody modeling in Hidden Markov Model based Text-to-Speech system (HTS). As a part of investigating the potential for building speech synthesis systems in new languages with li...
متن کامل