Segmental duration modelling in a text-to-speech system for the galician language
نویسندگان
چکیده
In this contribution we propose a segmental duration model for the Galician language. We have focused our work on the study of allophonic durations in their syllabic environment. Firstly, a study of the speech rate over a recorded corpus led us to consider different behaviours in certain types of sentences. Secondly, the corpus was analyzed in order to determine the main factors affecting duration (phonetic class, context, ...). Prosodic factors (stress and final lengthening) were found to be the most determinant, in quantitative terms, to predict timing. Finally, a model for assigning segmental durations is proposed.
منابع مشابه
Prosody modelling in Czech text-to-speech synthesis
This paper describes data-driven modelling of all three basic prosodic features – fundamental frequency, intensity and segmental duration – in the Czech text-to-speech system ARTIC. The fundamental frequency is generated by a model based on concatenation of automatically acquired intonational patterns. Intensity of synthesised speech is modelled by experimentally created rules which are in conf...
متن کاملThe New Slovenian Text-to-Speech System
Human-computer interaction in a natural language is becoming possible due to rapid development of computer power. While text-to-speech (TTS) systems for major world languages are quite advanced, smaller languages, like our Slovenian language, lack quality TTS synthesis. At the "Jozef Stefan" Institute a system called GOVOREC (SPEAKER) has been developed which is capable of automatic conversion ...
متن کاملLetter-to-sound Conversion for Galician Tts Systems
In this paper, a linguistically rule-based letter-to-sound (LTS) conversion algorithm is described for Galician language. A complete set of phonological transcription rules regarding the Galician standard variety is presented. A SAMPA computer readable phonetic alphabet for Galician is also proposed. The algorithm was implemented and tested by using CORGA text materials. The obtained experiment...
متن کاملQuantitative Modeling of Segmental Duration
In natural speech, durations of phonetic segments are strongly dependent on contextual factors. Quantitative descriptions of these contextual effects have appfications in text-to-speech synthesis and in automatic speech recognition. In this paper, we describe a speakerdependent system for predicting segmental duration from text, with emphasis on the statistical methods used for its construction...
متن کاملA hierarchical intonation model for synthesising F0 contours in galician language
In this contribution we propose a hierarchical intonation model for synthesising f0 contours with application to text-to-speech synthesis in Galician language. This model makes use of the implicit knowledge that resides in a database of natural f0 contours obtained from a read corpus. The novelty of this method lies on the way the f0 contour is generated. First, no phonological description in t...
متن کامل