The book discusses subjective ratings of quality and preference of unknown voices and dialog partners - their likability, for example. Human natural and artificial voices are studied in passive listening and interactive scenarios. In this book, the background, state of research, and contributions to the assessment and prediction of talker quality that is constituted in voice perception and in dialog are presented. Starting from theories and empirical findings from human interaction, major results and approaches are transferred to the domain of human-computer interaction (HCI). The main objective of this book is to contribute to the evaluation of spoken interaction in humans and between humans and computers, and in particular to the quality subsequently attributed to the speaking system or person based on the listening and interactive experience.
- Provides a comprehensive overview of research in evaluation of speakers and dialog partners;
- Presents recent results on the relevance of a first passive and interactive impression;
- Includes human and HCI evaluation results from a communicative perspective.
Benjamin Weiss studied communication science & phonetics, educational studies and Scandinavian studies at the universities of Bonn, Trondheim and Berlin. After his graduation in 2002, he was with the "Graduiertenkolleg" at the Linguistics department at Humboldt University Berlin, doing his dissertation on speech tempo and pronunciation. He received his Ph.D. in Linguistics in 2008. He joined the Quality and Usability Lab of the TU Berlin in January 2007, working on speech transmission quality, multimodal HCI, and speakers' likability. During that time, he was also Visiting Fellow at the MARCS Auditory Laboratories, University of Western Sydney, and at University of Technology Sydney, Australia. He has co-authored more than 50 reviewed papers and received his habilitation in Human-Computer Interaction in 2019. Benjamin Weiss is currently senior researcher at audEERING.
Theory: Foundations of Quality in Natural and Synthesized Speech.- Talker Quality in Passive Scenarios.- Talker Quality in Interactive Scenarios.- Talker Quality in Design and Evaluation of Speech-based Interactive Systems.