Predicting speech overlaps from speech tokens and co-occurring body behaviours in dyadic conversations.

Costanza Navarretta

Published in: ICMI (2013)

Keyphrases

speech recognition
speech signal
conversational speech
speech synthesis
automatic speech recognition
audio visual
speaker recognition
recognition engine
human communication
multi lingual
language acquisition
text to speech
database
multi stream
hidden markov models
multiresolution
information systems