A contribution to the synthesis of Italian intonation
نویسنده
چکیده
A first approximation of a model for the automatic synthesis of Italian intonation is proposed. In line with Pierrehumbert's theory of intonational description [1] fundamental frequency contours of Italian are modelled as sequences of abstract tonal elements aligned with the text. Different levels of prosodic phrasing (accent units, intermediate and intonational phrases) are taken into account in the intonational specification of a text string. The theoretical assumptions as well as the two stages ("text-to-phonology" and "phonology-to-phonetics") of the model's implementation in the textto-speech system are described.
منابع مشابه
Non-finality and pre-finality in bari Italian intonation: a preliminary account
In this paper, a preliminary account of intonational strategies used by Bari Italian speakers in signal non-finality and prefinality in discourse organisation is presented and discussed. Results obtained from auditory and instrumental analysis of speech material elicited with different methods (Map Task dialogues and monologues, lists readings) show that a rich inventory of intonational choices...
متن کاملParsing Defficulties & Phonological Processing in Italian
A recognition grammar to supply information to a text-to-speech system for the synthesis of Italian must rely heavily upon lexical information, in order to instantiate the appropriate grammatical relations. Italian is an almost free word order language which nonetheless adopts fa i r ly analysable strategies to move major constituents: some of these can strongly affect the functioning of the ph...
متن کاملOn the phonetics of rhythm of Italian: patterns of duration in pre-planned and spontaneous speech
This paper is concerned with the phonetic correlates of main stress in Italian and presents the analysis of the duration of syllabic nuclei in connected speech and in different speaking styles. Spontaneous dialogues are analysed basing on earlier works on pre-planned speech which investigated both [+stress] / [-stress] and stress/accent contrasts in Italian. The aim of this study is to examine ...
متن کاملImproved Syllable-Based Text to Speech Synthesis for Tone Language Systems
Speech Improved Syllable-Based Text to Speech Synthesis for Tone Language Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 Moses Ekpenyong, EmemObong Udoh, Escor Udosen, and Eno-Abasi Urua Slovak Automatic Dictation System for Judicial Domain. . . . . . . . . . . . . . . 16 Milan Rusko, Jozef Juhár, Marián Trnka, Ján Staš, Sakhia Darjaa...
متن کاملEstimation of the parameters of the quantitative intonation model with continuous wavelet analysis
Intonation generation in state-of-the-art speech synthesis requires the analysis of a large amount of data. Therefore reliable algorithms for the extraction of the parameters of an intonation model from a given F0 contour are required. This contribution proposes improvements concerning the extraction of the parameters of the quantitative intonation model developed by Fujisaki. The improvements ...
متن کامل