Towards intonation control in unit selection speech synthesis
نویسندگان
چکیده
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 compare segmental and joint-prosodic-and-segmental unit selection.
منابع مشابه
Study on Unit-Selection and Statistical Parametric Speech Synthesis Techniques
One of the interesting topics on multimedia domain is concerned with empowering computer in order to speech production. Speech synthesis is granting human abilities to the computer for speech production. Data-based approach and process-based approach are the two main approaches on speech synthesis. Each approach has its varied challenges. Unit-selection speech synthesis and statistical parametr...
متن کاملA Comprehensive Model of Intonation for Application in Speech Technology
This paper presents a new method of the stylization of intonation contours, which is the first step towards developing an intonation model for application in Polish unit selection speech synthesis. The paper starts with an overview of the existing F0 stylization algorithms underlying various intonation models followed by an overview of descriptions of Polish intonation. Then the assumptions beh...
متن کاملEffects of pitch accent type on interpreting information status in synthetic speech
Unit selection synthesis has made it possible to produce speech with high quality. However, because it allows little control over intonation, it may produce speech with contextually inappropriate intonation. In the signalling of information status, intonation, in particular, choice of pitch accent, has been taken into account in a number of dialogue systems. Previous research shows that this ca...
متن کاملInventory 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 کاملThe importance of segmental duration and f0 for generating more natural intonation in synthetic speech
This dissertation presents the importance of diphones’ duration and f0 information in generating more natural intonation in unit selection speech synthesis. The results showed that diphones’ duration or f0 information was highly correlated to one another due to the prosodic properties inherited from the recorded human speech. Also only raising the importance of duration and f0 information large...
متن کامل