An advanced intonation model for synthesis
نویسندگان
چکیده
The advanced intonation model for speech synthesis described here has a three level architecture. An initial abstract characterisation designed to represent intonation at the level of cognitive percept is rewritten to an intermediate representation which is speaker independent, yet which accurately reflects physical pitch contours. At this stage the contours lack the variability associated with natural speech. This representation is then further rewritten to provide an actual physical contour (now including variability and other ‘natural’ phenomena such as micro-intonation). One or two examples are given for stages one and two, and some indication of how we tackle stage three.
منابع مشابه
Inventory of intonation contours for text-to-speech synthesis
This paper presents an intonation model which determines intonation contours over intonation phrases. The model is described by four elements: communicative type of an intonation phrase; number of accent groups in it; position of the nuclear accent group in it; and set of target intonation points. Individualization of the model is based on semiautomatic analysis of speaker database. The model w...
متن کاملUsing decision trees within the tilt intonation model to predict F0 contours
This paper presents an intonation generation system for use in a text-to-speech synthesis system. The intonation generation system uses classification trees to predict intonation event location and regression trees to predict parameters relating to the F0 shape for the predicted events. The decision trees model intonation within the Tilt intonation model, which provides a parameterized descript...
متن کاملTowards intonation control in unit selection speech synthesis
We propose to control intonation in unit selection speech synthesis with a mixed CART-HMM intonation model. The Finite State Machine (FSM) formulation is suited to incorporate the intonation model in the unit selection framework because it allows for combination of models with different unit types and handling competing intonative variants. Subjective experiments have been carried out to compar...
متن کاملA Study on Detection of Intonation Events of Assamese Speech Required for Tilt Model
This paper has done a study and experimental analysis on different intonation events of Assamese speech. Assamese is a North East Indian language and spoken by lacks of people in India. The researchers need intonation model to identify language specific intonation events, which are necessary for synthesis process of that particular language. The paper shows outcomes of some experiments done wit...
متن کاملGenerating intonation from a mixed CART-HMM model for speech synthesis
This paper proposes two algorithms for generating intonation from a mixed CART-HMM intonation model for speech synthesis. Based either on a Viterbi search or on the Expectation-Maximization algorithm, the two generation algorithms are analyzed in terms of likelihood and F0 Root Mean Square Error. Listening tests are performed to subjectively evaluate the quality of the generated intonation.
متن کامل