SWING : A tool for modelling intonational varieties of Swedish

SWING (SWedish INtonation Generator) is a new tool for analysis and modelling of Swedish intonation by resynthesis. It was developed in order to facilitate analysis of regional varieties, particularly related to the Swedish prosody model. Annotated speech samples are resynthesized with rule based intonation and audiovisually analysed with regard to the major intonational varieties of Swedish. We find the tool useful in our work with testing and further developing the Swedish prosody model. Introduction and background Our object of study in the research project SIMULEKT (Simulating Intonational Varieties of Swedish, supported by the Swedish Research Council) (Bruce et. al, 2007) is the prosodic variation characteristic of different regions of the Swedish-speaking area, shown in Figure 1. Figure 1. Approximate geographical distribution of the seven main regional varieties of Swedish. The seven regions correspond to our present dialect classification scheme. In our work, the Swedish prosody model (Bruce & Gårding, 1978; Bruce & Granström, 1993; Bruce, 2007) and different forms of speech synthesis play prominent roles. Our main sources for analysis are the two Swedish speech databases SpeechDat (Elenius, 1999) and SweDia 2000 (Engstrand et.al, 1997). SpeechDat contains speech recorded over the telephone from 5000 speakers, registered by age, gender, current location and self-labelled dialect type. The research project SweDia 2000 collected a word list, an elicited prosody material and extensive spontaneous monologues from 12 speakers (younger and elderly men and women) each from more than 100 different places in Sweden and Swedishspeaking parts of Finland, selected for dialectal speech. The Swedish prosody model The main parameters for the Swedish prosody model are for word prosody 1) word accent timing, i.e. timing characteristics of pitch gestures of word accents (accent I/accent II) relative to a stressed syllable, and 2) pitch patterns of compounds, and for utterance prosody 3) intonational prominence levels (focal/non-focal accentuation), and 4) patterns of concatenation between pitch gestures of prominent words.