Non-Verbal Vocalisations and their Challenges: Emotion, Privacy, Sparseness, and Real Life

TL;DR

This paper reviews the history, types, and functions of Non-Verbal Vocalisations (NVVs), discusses challenges like privacy and data sparsity in modeling them, and advocates for corpus-based approaches for realistic AI applications.

Contribution

It provides a comprehensive overview of NVVs, highlights key challenges in their study, and proposes corpus-based methods as a solution for better modeling in AI.

Findings

NVVs convey emotional and paralinguistic information without semantic content.

Privacy and data sparsity are major challenges in NVV research.

Corpus-based approaches can improve realistic modeling of NVVs.

Abstract

Non-Verbal Vocalisations (NVVs) are short `non-word' utterances without proper linguistic (semantic) meaning but conveying connotations -- be this emotions/affects or other paralinguistic information. We start this contribution with a historic sketch: how they were addressed in psychology and linguistics in the last two centuries, how they were neglected later on, and how they came to the fore with the advent of emotion research. We then give an overview of types of NVVs (formal aspects) and functions of NVVs, exemplified with the typical NVV \textit{ah}. Interesting as they are, NVVs come, however, with a bunch of challenges that should be accounted for: Privacy and general ethical considerations prevent them of being recorded in real-life (private) scenarios to a sufficient extent. Isolated, prompted (acted) exemplars do not necessarily model NVVs in context; yet, this is the preferred strategy so far when modelling NVVs, especially in AI. To overcome these problems, we argue in favour of corpus-based approaches. This guarantees a more realistic modelling; however, we are still faced with privacy and sparse data problems.