Modeling of intonation bearing emphasis for TTS-synthesis of greek dialogues
نویسندگان
چکیده
TTS-synthesis of neutral style Greek with good intelligibility and quality has been achieved some time ago. As a further step towards expanding the applications domain of the TTS-system developed in our laboratory, the incorporation of emphasis into speech used in man-machine dialogues according to their context has been studied recently. In this paper the method applied for the analysis of intonation patterns, the results of this analysis, the algorithm established for the creation of desired intonation patterns and its implementation in the existing TTS-system for Greek is reported.
منابع مشابه
Maximum-likelihood dynamic intonation model for concatenative text-to-speech system
In this work we present a Maximum Likelihood (ML) joint pitch curve modeling, inspired by HMM TTS synthesis concept. This model provides an optimal solution for the coarse target intonation curve (3 points per syllable) and incorporates both static and dynamic pitch values for better utterance intonation modeling. The coarse intonation curve may be optionally combined with the original pitch ex...
متن کاملAn innovative F0 modeling approach for emphatic affirmative speech, applied to the Greek language
Prosody generation engine which is is responsible for the naturalness of the synthetic speech, remains one of the most important component of a Text-to-Speech synthesis system. In this paper we present an innovative algorithm for modelling the fundamental frequency F0 for the Greek language, for sentences containing emphatic segments. The main idea of our approach is the definition of a specifi...
متن کاملComparison of chironomic stylization versus statistical modeling of prosody for expressive speech synthesis
Chironomic stylization is the process of real-time modification of intonation contours (f0 and tempo) using drawing/writing gestures with a stylus on a graphic tablet. The question addressed in this research is whether hand-made intonation stylization could improve or degrade expressivity and overall quality, compared to statistical modeling of prosody. A system for expressive TTS in French bas...
متن کاملAutomatic modeling and implementation of intonation for the arabic language in TTS systems
This paper proposes a set of rules for the automatic generation of F0 contours for modern standard Arabic (MSA) affirmative and interrogative sentences. The objective is to finalize a model for the automatic processing of the intonative pattern in different TTS systems (e.g. synthesis by formants using Klatt synthesizer and synthesis by diphones, using a synthesizer based on PSOLA algorithm). T...
متن کاملEmphasis recreation for TTS using intonation atoms
We are interested in emphasis for text to speech synthesis. In speech to speech translation, emphasising the correct words is important to convey the underlying meaning of a message. In this paper, we propose to use a generalised command-response (CR) model of intonation to generate emphasis in synthetic speech. We first analyse the differences in the model parameters between emphasised words i...
متن کامل