Comparing phonetic changes in computer-directed and human-directed speech

This paper presents a study that examines the difference of certain pho-netic features between human-directed speech (HDS) and device-directed speech(DDS) in human-human-computer interactions. The corpus used for the analysesconsists of tasks performed by participants in cooperation with a human confederate and/or a computer-based interlocutor. This includes distributional and temporalanalyses, examining the similarities and differences of the overall distribution ofthe measured features and time-based changes throughout the interactions. Thefeatures fundamental frequency, intensity, and articulation rate were selected foranalysis. Results show significant differences in a majority of the cases for twoof the three selected features as well as insights regarding the participants’ speechbehavior during the interaction. These outcomes provide a look into further aspects of HDS and DDS and speech-related features in conversation analysis, whichmay help studies in topics like addressee detection or human-computer interaction(HCI).