Simulating Intonation in Regional Varieties of Swedish


Susanne Schötz, Lund University, Dept. of Linguistics and Phonetics, Centre for Languages and Literature
Jonas Beskow, Department of Speech, Music and Hearing, School of Computer Science and Communication, KTH
Gösta Bruce, Lund University, Dept. of Linguistics and Phonetics, Centre for Languages and Literature
Björn Granström, Joakim Gustafson, Department of Speech, Music and Hearing, School of Computer Science and Communication, KTH

Within the research project SIMULEKT (Simulating Intonational Varieties of Swedish), our recent work includes two approaches to simulating intonation in regional varieties of Swedish. The first involves a method for modelling intonation using the SWING (Swedish Intonation Generator) tool, where annotated speech samples are resynthesised with rule-based intonation and audio-visually analysed with regards to the major intonational varieties of Swedish. The second approach concerns a method for simulating dialects with HMM synthesis, where speech is generated from emphasis-tagged text. We consider both approaches important in our aim to test and further develop the Swedish prosody model, as well as to convincingly simulate Swedish regional varieties using speech synthesis.