Quantitative Laughter Detection, Measurement, and Classification—A Critical Survey

Abstract

The study of human nonverbal social behaviors has taken a more quantitative and computational approach in recent years due to the development of smart interfaces and virtual agents or robots able to interact socially. One of the most interesting nonverbal social behaviors, producing a characteristic vocal signal, is laughing. Laughter is produced in several different situations: in response to external physical, cognitive, or emotional stimuli; to negotiate social interactions; and also, pathologically, as a consequence of neural damage. For this reason, laughter has attracted researchers from many disciplines. A consequence of this multidisciplinarity is the absence of a holistic vision of this complex behavior: the methods of analysis and classification of laughter, as well as the terminology used, are heterogeneous; the findings sometimes contradictory and poorly documented. This survey aims at collecting and presenting objective measurement methods and results from a variety of different studies in different fields, to contribute to build a unified model and taxonomy of laughter. This could be successfully used for advances in several fields, from artificial intelligence and human-robot interaction to medicine and psychiatry.

Introduction to the Special Section: Convergence of Automation Technology, Biomedical Engineering, and Health Informatics Toward the Healthcare 4.0

“…The Caregiving Home seamlessly integrates all the smart devices in the home environment by heterogeneous but interoperable communication networks, collects exhaustively detailed data about human health and condition of infrastructure through various smart sensors [25]. It also performs broad data fusion, analytics, and decision making aided by AI [44][45][46]. Moreover, eventually it closes the loop by intelligent execution through all kinds of actuators, such as home automation devices, medical equipment, and home service or nursing robots.…”

“…Through technological innovation, robotics has drastically reshaped the landscape of healthcare both in its structure and its operation for the last decade [44], [53][54][55][56][57][58][59]. Healthcare robotics becomes one of the fastest growing field of robotics penetrating the fields of traditional medical treatment and healthcare with the most advanced robot technology, including surgical robots [60][61][62], catheter robotics [63][64][65][66], medication management robots [67], hygiene robots [68], and companion robots [69][70][71][72].…”

Speaker identification using laughter in a close social network

“…Petridis, Martinez and Pantic 2013), which might often be found written orthographically as 'ha' or 'haha'. In addition, whilst different scholars have used contradictory terminology to describe laughter's auditory properties in differing levels of detail, for the purposes of this study, laughter is understood to consist of calls, bouts, and episodes (Cosentino et al 2016;cf. for instance, Mowrer, LaPointe and Case 1987) which can be unvoiced, voiced, and mixed (Bachorowski, Smoski and Owren 2001;see Figures 2, 3 and 4 below).…”

“…The recordings from the elicitation sessions were uploaded to Praat 6.0.26 (Boersma and Weenink 2017). The onset and offset of laughter was identified at the episodic level (Cosentino et al 2016; see Literature Review, above) both auditorily and acoustically, and marked using Praat's TextGrids function. As the focus of this study is the audible element of laughter itself, respiration was not considered part of the laughter episodes, except for unavoidable cases when respiration occurred between two bouts that constituted one episode.…”

Automatic Recognition of Affective Laughter in Spontaneous Dyadic Interactions from Audiovisual Signals

“…Laughter is a non-verbal signal that plays a prominent role in many social situations [11], especially in social interactions where it is about 30 times more frequent than in solitary situations [39]. In general, laughter is considered as a universal social signal which is beneficial for health, as it has been shown to help in reducing stress [5], anxiety, pain and discomfort [28] and also improve the mood [31].…”