A metrical model of prosody for French TTS
نویسندگان
چکیده
The model of prosody used for French TTS in the Aculab TTS system is unusual in several respects. Firstly, it is based firmly on current metrical theories of French prosody. Secondly, it is entirely knowledge-based: there are no stochastic components in the model. Thirdly, it makes use of a pseudo-random element to avoid the predictability of synthetic prosody. Fourthly, it is designed to facilitate adaptation to other languages, particularly languages with similar prosody such as Spanish and Italian. The design and implementation of this model are presented here, as well as our plans for its extension to other languages.
منابع مشابه
Synthesizing Elaborate Intonation Contours in Text-to-Speech for French
This paper presents a modular TTS system (called MINGUS) which exploits syntactic information contained in the input and allows additional annotation of the input in order to obtain particular intonation contours or to vary most prosodic parameters. This system is based on a tonal representation of French intonation, on a model of the interaction between syntax and prosody, and on a model of th...
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 کاملA joint prosody evaluation of French text-to-speech synthesis systems
This paper reports on prosodic evaluation in the framework of the EVALDA/EvaSy project for text-to-speech (TTS) evaluation for the French language. Prosody is evaluated using a prosodic transplantation paradigm. Intonation contours generated by the synthesis systems are transplanted on a common segmental content. Both diphone based synthesis and natural speech are used. Five TTS systems are tes...
متن کاملVariations in the realization of the French Accentual Phrase in the light of language contact
In this paper we discuss French prosody in the light of language contact. Data of three contact varieties of French are compared with two varieties spoken in monolingual contexts. The data are semi-automatically processed, and three prosodic features are analyzed: metrical weight of the Accentual Phrases (AP), respect of AP formation constraints, and realizations of sandhi phenomena. Rhythmic c...
متن کاملPerformance Analysis of Text To Speech Synthesis System Using HMM And Prosody Features With Parsing For Tamil Language
This paper describes a Hidden Markov Model (HMM) based (TTS) system and prosody based (TTS) system for producing natural sounding synthetic speech in Tamil language. The (HMM) based system consists of two phases such as training and synthesis. Tamil speech is first parameterized into spectral and excitation features using Glottal Inverse Filtering (GIF). An emotions present in the input text is...
متن کامل