Perception in Multimodal Dialogue Systems

Volume 5078 of the series Lecture Notes in Computer Science pp 293-296

EXPROS: A Toolkit for Exploratory Experimentation with Prosody in Customized Diphone Voices

  • Joakim GustafsonAffiliated withKTH Speech Music and Hearing
  • , Jens EdlundAffiliated withKTH Speech Music and Hearing

* Final gross prices may vary according to local VAT.

Get Access


This paper presents a toolkit for experimentation with prosody in diphone voices. Prosodic features play an important role for aspects of human-human spoken dialogue that are largely unexploited in current spoken dialogue systems. The toolkit contains tools for recording utterances for a number of purposes. Examples include extraction of prosodic features such as pitch, intensity and duration for transplantation onto synthetic utterances, and creation of purpose-built customized MBROLA mini-voices.