Human speech consists of both Verbal and Nonverbal sounds. Nonverbal sounds such as paralinguistics and expressive voices, along with emotional speech, play an important role in human communication. Nonverbal speech sounds not only convey important non-linguistic information, but also carry linguistic content in some cases. For example, emotional audio-visual signals carry linguistic information along with the emotions that convey the physical and mental state of a human being. Several studies have explored different signal processing methods and features for analysing the paralinguistic sounds and expressive voices. Different approaches for emotion classification have also been examined. Few studies have also attempted developing automated systems for emotion recognition However, much research work is still required for a range of diverse practical applications. Hence, in this paper, different databases, signal processing methods, features extracted, classifiers used for analyses of paralinguistic sounds and expressive voices, performance evaluation results and diverse applications are reviewed. The objective of this paper is to present the diverse information related to this domain in a concise manner and at a single place, that can be quite helpful to the beginners as well as experts in this domain. This paper should also help further research work in this direction.
Cite as: Kadali, D.B., Mittal, V.K. (2020) Studies on Paralinguistic Sounds, Emotional Speech and Expressive Voices. Proc. Workshop on Speech, Music and Mind (SMM 2020), 11-15, doi: 10.21437/SMM.2020-3
@inproceedings{kadali20_smm,
author={Devi Bhavani Kadali and Vinay Kumar Mittal},
title={{Studies on Paralinguistic Sounds, Emotional Speech and Expressive Voices}},
year=2020,
booktitle={Proc. Workshop on Speech, Music and Mind (SMM 2020)},
pages={11--15},
doi={10.21437/SMM.2020-3}
}