Zofia Malisz

I am a postdoc in speech technology at TMH, KTH. 

My work focuses on modelling speech prosody (rhythm, timing and prominence), multimodal dialogue (prosodic modelling of feedback functions, head gestures) and phonation (glottalisation, VOT).

I was also involved in developing listening behaviour in artificial agents and in building multimodal corpora.

At KTH, I am responsible for the modelling of prominence in a text-to-speech synthesis project Wikispeech.