Speech, Music and Hearing
SE-100 44 STOCKHOLM, SWEDEN
TEL: +46 8 790 7856
FAX: +46 8 790 7854
My research focuses on developing flexible spoken utterance generation which to a large extent follows the principles of human-human communication. In conversation humans can choose to say something in a number of different ways but the choice is not arbitrary. Depending on what we want to communicate we consider different linguistic choices available in the current context. A natural part of human conversation is to adapt what we say and how we say it depending on our conversational partners and the dialogue context. This includes syntactic, semantic and lexical variation. My thesis work focuses on analysis of human behaviours which are typically not modelled in spoken dialogue systems. These behaviours include cue phrases, hesitations, false starts, repetitions and fragmental utterances. I has also studied the effect of various turn-taking cues with both human and synthetic voice.
From September 2009 until the end of January 2010 I was a visiting scholar at Columbia University working on a project together with Noémie Elhadad at Department of Biomedical Informatics and Julia Hirschberg at the Department of Computer Science granted by the Simons Foundation.