No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
On the Sound of Successful Meetings: How Speech Prosody Predicts Meeting Performance
Abstract
This paper investigates the degree to which meeting success can be predicted through holistic, acoustic-prosodic measurements. The analyzed meetings are taken from the Parking Lot Corpus in which 70 groups of three to six students discuss the traffic situation at their university and come up with parking and transportation recommendations. The number, feasibility, and quality of these recommendations as well as the mean effectiveness and satisfaction ratings across group members provide the basis for correlations with three sets 15 acoustic-prosodic features that cover pitch, duration/timing, intensity, and the absolute frequencies of local events such as silent pauses. Results show that meeting success is, in fact, considerably correlated with the overall “sound” of the individual meetings, with pitch features being the most diverse and powerful predictors. In addition, we found that the “sound” of subjectively effective meetings differs from the “sound” of objectively productive meetings, i.e. meetings that generate a high output of feasible and/or high-quality recommendations. The prosodic feature patterns suggest that effective meetings are short and matter-of-fact, whereas the productive meetings are longer and have a lively speech melody that makes these meetings stimulating. We discuss the implications of our findings for future research and technological innovation.
... e.g., [9]) influence the way of communicating in the group (e.g., [6,7,10]). As already stated in [11]: ...
... Regarding the meetings' outcome, two different interpretations can be seen: (1) The classical way, where the outcome relates to specific goals or results and thus, can be assessed in terms like effectiveness; (2) The interpretations discussed in [11] where a more socialising perspective is being considered. ...
... Regarding, at first, the second aspect, being mainly related to longer-lasting meetings that are rather considered not as effective, the authors of [11] argue: ...
Humans are considered to be communicative, usually interacting in dyads or groups. In this paper, we investigate group interactions regarding performance in a rather formal gathering. In particular, a collection of ten performance indicators used in social group sciences is used to assess the outcomes of the meetings in this manuscript, in an automatic, machine learning-based way. For this, the Parking Lot Corpus, comprising 70 meetings in total, is analysed. At first, we obtain baseline results for the automatic prediction of performance results on the corpus. This is the first time the Parking Lot Corpus is tapped in this sense. Additionally, we compare baseline values to those obtained, utilising bidirectional long-short term memories. For multiple performance indicators, improvements in the baseline results are able to be achieved. Furthermore, the experiments showed a trend that the acoustic material of the remaining group should use for the prediction of team performance.
... The use of objective data on meeting participation and other attributes is central to our approach as it enables at-scale and ultimately passive measurement of meeting experiences [81]. Meeting effectiveness, and especially inclusiveness, are both complex constructs with many subjective elements that are difficult to currently capture using objective measures (e.g., [49,61]); hence, we relied on survey ratings to measure these. However, the ultimate aim of our approach for real-world deployment is to build a predictive model using objective telemetry that can accurately estimate meeting effectiveness and inclusiveness without the need for survey ratings. ...
... Third, the dynamics of participation, including patterns in turn-taking and other aspects of conversation flow, can yield rich insights into effectiveness and inclusiveness in a privacy-preserving manner (i.e., without considering the content of speech) [26,44,60]. Potentially fruitful data here includes patterns in the timing and duration of speech across participants [44], choral responses like laughter [13], acoustic features like prosody [49], gestures such as head nods [65], and eye gaze patterns [21]. ...
Workplace meetings are vital to organizational collaboration, yet relatively little progress has been made toward measuring meeting effectiveness and inclusiveness at scale. The recent rise in remote and hybrid meetings represents an opportunity to do so via computer-mediated communication (CMC) systems. Here, we share the results of an effective and inclusive meetings survey embedded within a CMC system in a diverse set of companies and organizations. We link the survey results with objective metrics available from the CMC system to identify the generalizable attributes that characterize perceived effectiveness and inclusiveness in meetings. Additionally, we explore a predictive model of meeting effectiveness and inclusiveness based solely on objective meeting attributes. Lastly, we show challenges and discuss solutions around the subjective measurement of meeting experiences. To our knowledge, this is the largest data-driven study conducted after the pandemic peak to measure and understand effectiveness and inclusiveness in real-world meetings.
... Here we can only speculate what causes this effect; one possibility may be that when a team leader is less charismatic, the team will stand more together. The finding is related to a similar observation made in Niebuhr et al. (2021) on "the sound of successful meetings". Based on a corpus of 70 idea-generation meetings of teams of 3-4 US highschool students, the authors investigated whether and how the interlocutors' prosody correlates with the subjective and objective performance indicators of such creativity-oriented meetings. ...
This study examines whether a social robot can enable team creativity and increase team performance depending on its speaking style. The aim is to provide insight into human teams' creativity and performance when exposed to different ways of speaking by a social robot, that is, when the robotic creativity facilitator is using different acoustic-prosodic features. In one condition, participants received their instructions from the robot in a “charismatic” speaking style, in the other, the robot used a less engaging way of speaking. The results show that when the robot's speech is based on charismatic speech characteristics, it is significantly better at enhancing team creativity and performance than when its speech uses fewer charismatic speech characteristics. The robot's speaking style thus influences its effectiveness as team creativity facilitator.
... The first three parameters have been shown in previous studies to correlate robustly with perceived speaker charisma [15,17,18,19]. The other two parameters were added because they were recently found to correlate with meeting effectiveness and creativity in teams, two areas of thought and action closely related to charismatic leadership [27]. All pitch parameters are assumed to be positively correlated with speaker charisma. ...
Workplace meetings are vital to organizational collaboration, yet relatively little progress has been made toward measuring meeting effectiveness and inclusiveness at scale. The recent rise in remote and hybrid meetings represents an opportunity to do so via computer-mediated communication (CMC) systems. Here, we share the results of an effective and inclusive meetings survey embedded within a CMC system in a diverse set of companies and organizations. We correlate the survey results with objective metrics available from the CMC system to identify the generalizable attributes that characterize perceived effectiveness and inclusiveness in meetings. Additionally, we explore a predictive model of meeting effectiveness and inclusiveness based solely on objective meeting attributes. Lastly, we show challenges and discuss solutions around the subjective measurement of meeting experiences. To our knowledge, this is the largest data-driven study conducted after the pandemic peak to measure, understand, and predict effectiveness and inclusiveness in real-world meetings at an organizational scale.
Charismatic speaking skills, particularly those of the voice, are known to be an important asset of managers, politicians, and even teachers. Students have so far been less in the limelight in this regard, although modern collaborative-learning and oral-examination concepts suggest that vocal charisma can already be a decisive factor for study success as well. The present paper examines this question based on 82 electrical-engineering students. Their initial self-introductions in front of the other fellow students were analyzed using a new acoustic technology that translates 16 voice features into a total vocal charisma (PASCAL) score. Results show that these PASCAL scores are overall low (i.e. improvable) and positively correlated with the oral exam grades of both individual students and student teams. Moreover, the teams' PASCAL scores positively correlate with the per-formance in the "Marshmallow Challenge", i.e. a creative teamwork task. Additional in-depth analyses show that teams without any above-average charismatic student performed worst, but that teams with more than one above-average charismatic student struggled with leadership conflicts and solo actions. We interpret our findings as a strong plea for (vocal) charisma analysis to be integrated in higher-education practice both for managing team dynamics and performance and for increasing individual study success.
Sociological research on vocal dynamics demonstrates that as actors engage in conversation, their vocal frequencies tend to converge over time. Previous scholars have theorized that patterns of vocal accommodation serve as a mechanism through which speakers non-consciously communicate perceptions of each other’s relative status. In this article I discuss existing evidence linking vocal accommodation to status perceptions. Next, I report results from a laboratory experiment in which I test the proposed causal link between status and vocal accommodation by randomly assigning members of dyadic task groups to occupy either a higher or lower status position and assessing patterns of vocal accommodation. Results support the theorized causal relationship between group status structure and vocal accommodation. I argue that, as an unobtrusive and non-conscious indicator of status, vocal accommodation is a valuable, yet underused tool for assessing group status structures in a wide variety of situations and regarding many substantive sociological questions.
An important aspect of human emotion perception is the use of contextual information to understand others' feelings even in situations where their behavior is not very expressive or has an emotionally ambiguous meaning. For technology to successfully detect affect, it must mimic this human ability when analyzing audiovisual input. Databases upon which machine learning algorithms are trained should capture the context of social interactions as well as the behavior expressed in them. However, there is a lack of consensus about what constitutes relevant context in such databases. In this article, we make two contributions towards overcoming this challenge: (a) we identify two principal sources of context for emotion perceptions based on psychological theory, and (b) we provide an overview of how each of these has been considered in published databases covering social interactions. Our results show that a similar set of contextual features are present across the reviewed databases. Between all the different databases researchers seem to have taken into account a set of contextual features reflecting the sources of context seen in psychological theory. However, within individual databases, these features are not yet systematically varied. This is problematic because it prevents them from being used directly as resources for the modeling of context-sensitive affect detection. Based on our findings, we suggest improvements for the future development of affective databases.
Intonation is a multitasker. It conveys a plethora of non-lexical meanings and functions, and mirrors a speaker's personality traits, one of them being charisma. In the age in which leaders communicate globally through digital mass media, speaker charisma has become an important field of research. The number of different f0 level and range measures that are used, not only in phonetics, to determine speaker charisma call for standardization. Which f0 measures correlate most strongly with perceived speaker charisma and should thus be used in future analyses? Our study addresses this question based on 51 speakers whose charisma was rated by 42 listeners. Results show that the f0 mean is the best parameter to measure perceived charisma in terms of pitch level, while the best pitch distribution measures are kurtosis and the 80-percentile f0 range. The results are discussed in terms of gender differences and issues of cross-linguistic generalization.
Meetings are routine in organizations, but their value is often questioned by the employees who must sit through them daily. The science of meetings that has emerged as of late provides necessary direction toward improving meetings, but an evaluation of the current state of the science is much needed. In this review, we examine current directions for the psychological science of workplace meetings, with a focus on applying scientific findings about the activities that occur before, during, and after meetings that facilitate success. We conclude with concrete recommendations and a checklist for promoting good meetings, as well as some thoughts on the future of the science of workplace meetings.
Today, in technical dialog-systems diverse solutions are implemented to detect if a system should react to an uttered speech command. Typically used solutions are push-to-talk and keywords. Unfortunately, these solutions constitute an unnatural interaction to overcome the problem that the system is not able to detect
when it is addressed. Moreover, the actual preferred keyword method can result in confusions when the keyword has been said but no interaction with the system was intended by the user. Therefore, technical systems should be able to perform an addressee detection. Various aspects have already been investigated in this field of research, however most of them pursue a multimodal approach including textual
and/or visual information achieving up to 93% unweighted average recall.
In our research, we limit ourselves to the pure acoustic information, as we assume that humans are talking differently to technical systems than to humans. Considering speakers of different age-, sex- and technical background-groups, we analysed how a technical system and another human being is being addressed on two subsets. An addressee detection system based on acoustics was utilized and it was investigated to which extent the different speaker groups influence the recognition rate in inter- and intra-group experiments. Our approach achieves competitive results of 84.45% to 98.06% unweighted average recall and 88.35% to 95.63% F1score.
Interactions that occur prior to a meeting constitute premeeting talk (PMT). Of the different PMT types, research suggests that small talk PMT is especially meaningful. In this study, meeting participants’ interactions both prior to and during the meeting were video recorded, coded into sense units, and classified by coding schemes. This study investigated the influence of small talk PMT on both perceived and objective group performances, as well as the potential for positive socioemotional and problem-focused statements to serve as mediators. The results supported the mediating influence of both types of statements for only perceived performance. Our results suggest that a group-level babble effect can take place in meetings, such that groups who engage in more extensive discussion tend to believe that they achieved high performance, but objective ratings do not support this belief. Theoretical and practical implications, limitations of the study, and future research opportunities are discussed.
Communication accommodation theory (CAT) is a general theoretical framework for both interpersonal and intergroup communication. It seeks to explain and predict why, when, and how people adjust their communicative behavior during social interaction (including mediated contact), and what social consequences might result from such adjustments. This entry provides an overview of what constitutes accommodative and nonaccommodative moves (with particular attention devoted, albeit not exclusively, to convergence and divergence). Previous CAT principles are modestly refined, and directions for future research suggested.
Researchers from a variety of disciplines are currently working with NASA to prepare for human exploration of Mars in the next decades. Such exploration will take scientific discovery to new heights, providing unprecedented information about the geology, atmosphere, and potential for life on Mars, including previous life, current life, and perhaps even our own lives in the future. To make these unparalleled discoveries, however, astronauts will need to undertake a novel and unprecedented journey. Moreover, the mission to Mars will require a team of crew members who will have to endure and sustain team performance requirements never seen before. Multidisciplinary teams of scientists have begun to provide the needed steps to address this challenge. The purpose of this article is (a) to illustrate the kinds of new conceptual frameworks and paradigms needed for teams in space exploration, (b) to delineate promising research paths to ensure that a robust team science can emerge for long-duration space exploration (LDSE), (c) to showcase initial findings and insights from studying astronauts now, and (d) to outline a plan of action for team-effectiveness research in LDSE.
The aim of our paper is to identify the role of emotional intelligence in developing communication and relational skills. Evaluating the level of emotional intelligence is essential for building efficient communication, intellectual and emotional development. Socrate's advice “Know thyself!” finds its application in this case by (self)controlling one's emotions and adjusting them to the context, aiming at the need to know others and interact positively, skills that bring satisfaction and accomplishments to the human being on an individual as well as social level. The paper attends to these imperatives.
Research on humor in organizations has rarely considered the social context in which humor occurs. One such social setting that most of us experience on a daily basis concerns the team context. Building on recent theorizing about the humor-performance link in teams, this study seeks to increase our understanding of the function and effects of humor in team interaction settings. We examined behavioral patterns of humor and laughter in real teams by videotaping and coding humor and laughter during 54 regular organizational team meetings. Performance ratings were obtained immediately following the team meetings as well as at a later time point from the teams' supervisors. At the behavioral unit level within the team interaction process, lag sequential analysis identified humor and laughter patterns occurring above chance (e.g., a joke followed by laughter, followed by another joke). Moreover, humor patterns triggered positive socioemotional communication, procedural structure, and new solutions. At the team level, humor patterns (but not humor or laughter alone) positively related to team performance, both immediately and 2 years later. Team-level job insecurity climate was identified as a boundary condition: In low job insecurity climate conditions, humor patterns were positively related to performance, whereas in high job insecurity climate conditions, humor patterns did not relate to team performance. The role of job insecurity as a boundary condition persisted at both time points. These findings underscore the importance of studying team interactions for understanding the role of humor in organizations and considering team-level boundary conditions over time. (PsycINFO Database Record (c) 2014 APA, all rights reserved).
Building on a social identity framework, our cross-level process model explains how a manager’s servant leadership affects frontline employees’ service performance, measured as service quality, customer-focused citizenship behavior, and customer-oriented prosocial behavior. Among a sample of 238 hairstylists in 30 salons and 470 of their customers, we found that hair stylists’ self identity embedded in the group, namely self-efficacy and group identification, partially mediated the positive effect of salon managers’ servant leadership on stylists’ service performance as rated by the customers, after taking into account the positive influence of transformational leadership. Moreover, group competition climate strengthened the positive relationship between self-efficacy and service performance.
The present study was conducted to determine the extent to which different nonverbal behaviors were associated with romantic interest in a highly attractive confederate and whether these behaviors differed as a function of relationship status and self-reported love for one’s partner. Mimicry was positively associated with romantic interest in the confederate, and consistent with the devaluation hypothesis, mimicry was negatively associated with self-reported love for one’s partner, suggesting that mimicry functions to signal preferred social distance. In addition, smiling and vocal pleasantness emerged as important affiliative nonverbal behaviors. The present results suggest that mimicry acts as a relationship-maintenance mechanism, one that is expressed automatically, unintentionally, and nonconsciously. Implications for the role of nonconscious mimicry in romantic attraction and relationship-maintenance processes are discussed.
In this paper, an overview of human-robot interactive communication is
presented, covering verbal as well as non-verbal aspects of human-robot
interaction. Following a historical introduction, and motivation towards fluid
human-robot communication, ten desiderata are proposed, which provide an
organizational axis both of recent as well as of future research on human-robot
communication. Then, the ten desiderata are examined in detail, culminating to
a unifying discussion, and a forward-looking conclusion.
This study explores the relationships among transformational leadership style, cognitive trust, and collective efficacy as well as the impact of these variables on distal team performance. Data collected from 39 teams find that team cognitive trust as two process variables involves a transformational leadership process in which cognitive trust in the team leader and cognitive trust among team members mediate the impact of this leadership style on collective efficacy. Unlike previous studies, our results show that leveraging cognitive trust in the team leader is necessary but not sufficient for better proximal collective efficacy, which in turn facilitates distal team performance. Although cognitive trust among team members was more closely related to proximal collective efficacy than cognitive trust in the team leader was, the factors that foster the development of cognitive trust among team members remain scantly explored in the transformational leadership literature and deserve more attention in future research.
Employee engagement is a positive, fulfilling, work-related state of mind characterized by vigor, dedication, and absorption. Using Kahn’s theory of engagement, we look at an organizational context where employee engagement may be promoted—the workgroup meeting. Two time-separated Internet-based surveys were used to query a sample of working adults (N = 319). The findings provide support that the psychological conditions for engagement mediate the relationship between manager usage/facilitation of meetings and overall employee engagement. Specifically, as managers make their workgroup meetings relevant, allow for employee voice in their meetings where possible, and manage the meeting from a time perspective, employees appear poised to fully engage themselves in their work in general. The results suggest that managers can use a common workplace activity, workgroup meetings, to engage their employees when they use/facilitate meetings in an effective manner.
This study explored links between emotional intelligence, measured as a set of abilities, and personality traits, as well as the contribution of both to the perceived quality of one's interpersonal relationships. In a sample of 103 college students, we found that both emotional intelligence and personality traits were associated with concurrent self-reports of satisfaction with social relationships. Individuals scoring highly on the managing emotions subscale of the Mayer, Salovey, and Caruso Emotional Intelligence Test (MSCEIT), were more likely to report positive relations with others, as well as perceived parental support, and less likely to report negative interactions with close friends. These associations remained statistically significant even controlling for significant Big Five personality traits and verbal intelligence. Global satisfaction with one's relationships was associated with extraversion, neuroticism (negatively), and the ability to manage one's emotions, as assessed by the MSCEIT.
Recently important changes have been made to fire service management practices in Australia; however, these changes have typically not been based on empirical research or followed up by systematic evaluation. While job satisfaction and leadership behaviour have been extensively investigated in other fields, studies of these variables in the fire service, particularly in Australia, are almost absent. This article examines links between job satisfaction and leadership behaviour in aviation fire fighters. Fifty-six fire fighters responded to the Job Descriptive Index and the Leadership Behaviour Questionnaire XII. As hypothesised, employee job satisfaction correlated with supervisor leadership behaviour, with the exception of consideration leadership and co-worker satisfaction. A new explanation, concerning level of team interaction, is proposed for the findings. Implications for the fire service and areas for further research are suggested.
We review and synthesize the research literature examining group affect and its consequences, focusing on groups who interact together to accomplish a task. We use a definition of group affect that incorporates the mutual influence of a group’s affective context and affective composition (the amalgamation of group members’ state and trait affect). Our focus is on the influence of group affect on individual members’ behaviors and attitudes and on group-level outcomes. We call for more research in this area, including the study of more specific discrete group emotions and a broadening of the types of groups studied in this research area.
Synchrony refers to individuals' temporal coordination during social interactions. The analysis of this phenomenon is complex, requiring the perception and integration of multimodal communicative signals. The evaluation of synchrony has received multidisciplinary attention because of its role in early development, language learning, and social connection. Originally studied by developmental psychologists, synchrony has now captured the interest of researchers in such fields as social signal processing, robotics, and machine learning. This paper emphasizes the current questions asked by synchrony evaluation and the state-of-the-art related methods. First, we present definitions and functions of synchrony in youth and adulthood. Next, we review the noncomputational and computational approaches of annotating, evaluating, and modeling interactional synchrony. Finally, the current limitations and future research directions in the fields of developmental robotics, social robotics, and clinical studies are discussed.
Since the 1940s, social psychologists have conducted research testing whether it is possible to accurately identify members of perceptually ambiguous groups. This study quantitatively reviews the research on the perception of ambiguous groups to better understand the human capacity to accurately identify others based on very subtle nonverbal cues. Standard random-effects meta-analytic techniques were used to examine the distinctions between different target groups in terms of their identifiability, as well as to compare rates of accuracy across perceptual modalities (e.g., photographs, audio, video) and other study design differences. Overall, the accuracy of identifying targets was significantly better than chance guessing (i.e., 64.5%). Furthermore, stimulus modality was found to be a moderator of accuracy. Other moderators (e.g., time of exposure, analytic approach) were identified and examined. These data help to document and characterize broad trends in the proliferating and expanding study of the perception and categorization of ambiguous social groups.
The analysis of authentic speech, unlike that of laboratory speech, needs to take into account the fact that the fundamental frequency patterns corresponding to the intonation of utterances can be of two types -local pitch characteristics determined by the surface phonological representation of the intonation and longer term characteristics corresponding to less well understood changes in pitch key and range. In this paper a number of acoustic correlates of changes in pitch key and range are examined and compared to subjective annotations and a preliminary attempt is made to estimate these changes automatically.
Previous relationship research has largely ignored the importance of similarity in how people talk with one another. Using natural language samples, we investigated whether similarity in dyads' use of function words, called language style matching (LSM), predicts outcomes for romantic relationships. In Study 1, greater LSM in transcripts of 40 speed dates predicted increased likelihood of mutual romantic interest (odds ratio = 3.05). Overall, 33.3% of pairs with LSM above the median mutually desired future contact, compared with 9.1% of pairs with LSM at or below the median. In Study 2, LSM in 86 couples' instant messages positively predicted relationship stability at a 3-month follow-up (odds ratio = 1.95). Specifically, 76.7% of couples with LSM greater than the median were still dating at the follow-up, compared with 53.5% of couples with LSM at or below the median. LSM appears to reflect implicit interpersonal processes central to romantic relationships.
The automated extraction of semantically meaningful information from multi-modal data is becoming increasingly necessary due to the escalation of captured data for archival. A novel area of multi-modal data labelling, which has received relatively little attention, is the automatic estimation of the most dominant person in a group meeting. In this paper, we provide a framework for detecting dominance in group meetings using different audio and video cues. We show that by using a simple model for dominance estimation we can obtain promising results.
In this article, we describe a method for automatically detecting syllable nuclei in order to measure speech rate without the need for a transcription. A script written in the software program Praat (Boersma & Weenink, 2007) detects syllables in running speech. Peaks in intensity (dB) that are preceded and followed by dips in intensity are considered to be potential syllable nuclei. The script subsequently discards peaks that are not voiced. Testing the resulting syllable counts of this script on two corpora of spoken Dutch, we obtained high correlations between speech rate calculated from human syllable counts and speech rate calculated from automatically determined syllable counts. We conclude that a syllable count measured in this automatic fashion suffices to reliably assess and compare speech rates between participants and tasks.
Firefighters routinely encounter physical demands that contribute to countless musculoskeletal injuries. Seemingly, a progressive prescription for fitness would offer superior protection against intrinsic job risks. The purpose of this study was to investigate the influence of two resistance training interventions on fitness adaptations among firefighters, and to assess the degree of transfer to job-specific tasks. Firefighter trainees were recruited for participation in this experimental study. Two distinct, periodized training models-undulation training (UT; n = 7) and standard training control (STCo; n = 7)-were used to determine the differential affects for muscular fitness and transference to firefighter performance batteries. Specific tests were administered to evaluate 1) upper- and lower-body muscular strength, 2) lower-body power output, 3) sprint speed and jumping ability, 4) anthropometry, and 5) firefighter Grinder performance (i.e., firefighter-specific job tests). The 9-week UT experimental treatment prescription was characterized by daily "nonlinear" fluctuations in training to preferentially elicit specific and distinct muscular fitness components, whereas the STCo treatment conformed to a traditional model, in which each fitness component was systematically targeted during a specified mesocycle. For both treatments, nearly all fitness and performance measures significantly increased from baseline (p < 0.05), with a trend in favor of UT. Further, the UT group experienced significantly greater improvements (p < 0.05) in Grinder performance over the STCo group. Calculation of effect sizes identified meaningful differences in the magnitude of changes in outcomes (effect size > 0.50) in favor of UT for measures of thigh circumference, vertical jump, 1RM squat, Grinder performance, and peak power output. These findings suggest a potentially greater stimulus for multidimensional muscular fitness development with UT, over a periodized STCo. This study effectively establishes that UT may offer a greater transference to performance for firefighter-specific job tasks.
Professional actors' portrayals of 14 emotions varying in intensity and valence were presented to judges. The results on decoding replicate earlier findings on the ability of judges to infer vocally expressed emotions with much-better-than-chance accuracy, including consistently found differences in the recognizability of different emotions. A total of 224 portrayals were subjected to digital acoustic analysis to obtain profiles of vocal parameters for different emotions. The data suggest that vocal parameters not only index the degree of intensity typical for different emotions but also differentiate valence or quality aspects. The data are also used to test theoretical predictions on vocal patterning based on the component process model of emotion (K.R. Scherer, 1986). Although most hypotheses are supported, some need to be revised on the basis of the empirical evidence. Discriminant analysis and jackknifing show remarkably high hit rates and patterns of confusion that closely mirror those found for listener-judges.
For many years, meeting satisfaction has been a key outcome variable in experimental group support systems (GSS) research. GSS research results on meeting satisfaction are conflicting, reporting positive, negative, or no effects. Unfortunately, no causal model of meeting satisfaction has been developed that could explain these effects. This paper derives satisfaction attainment theory (SAT), a causal model of meeting satisfaction. It further presents a survey instrument for measuring the constructs in the model. This instrument was statistically validated with a field study involving 156 working professionals. Furthermore, the field study provided support for the hypotheses that were derived from SAT's propositions. A number of implications for future GSS research on meeting satisfaction are identified.
The goal of addressee detection is to answer the question ‘Are you addressing me?’ In order to participate in multiparty conversations, a spoken dialogue system is supposed to determine whether a user is addressing the system or another human. The present paper describes three levels of speech and text analysis (acoustical, lexical, and syntactical) for multimodal addressee detection and reveals the connection between them and the classification performance for different categories of speech. We propose several classification models and compare their performance with the results of the original research performed by the authors of the Smart Video Corpus which we use in our computations. Our most effective meta-classifier working with acoustical, syntactical, and lexical features provides an unweighted average recall equal to 0.917, showing a nine percent advantage over the best baseline model, though the baseline classifier additionally uses head orientation data. We also propose an LSTM neural network for text classification which replaces the lexical and the syntactical classifier by a single model reaching the same performance as the most effective meta-classifier does, despite the fact that this meta-model additionally analyses acoustical data.
The goal of addressee detection is to answer the question , “Are you talking to me?” When a dialogue system interacts with multiple users, it is crucial to detect when a user is speaking to the system as opposed to another person. We study this problem in a multimodal scenario, using lexical, acoustic, visual, dialogue state, and beamforming information. Using data from a multiparty dialogue system, we quantify the benefits of using multiple modalities over using a single modality. We also assess the relative importance of the various modalities, as well as of key individual features, in estimating the addressee. We find that energy-based acoustic features are by far the most important, that information from speech recognition and system state is useful as well, and that visual and beamforming features provide little additional benefit. While we find that head pose is affected by whom the speaker is addressing, it yields little nonredundant information due to the system acting as a situational attractor. Our findings would be relevant to multiparty, open-world dialogue systems in which the agent plays an active, conversational role, such as an interactive assistant deployed in a public, open space. For these scenarios , our study suggests that acoustic, lexical, and system-state information is an effective and practical combination of modalities to use for addressee detection. We also consider how our analyses might be affected by the ongoing development of more realistic, natural dialogue systems.
This first volume to analyze the science of meetings offers a unique perspective on an integral part of contemporary work life. More than just a tool for improving individual and organizational effectiveness and well-being, meetings provide a window into the very essence of organizations and employees' experiences with the organization. The average employee attends at least three meetings per week and managers spend the majority of their time in meetings. Meetings can raise individuals, teams, and organizations to tremendous levels of achievement. However, they can also undermine effectiveness and well-being. The Cambridge Handbook of Meeting Science assembles leading authors in industrial and organizational psychology, management, marketing, organizational behavior, anthropology, sociology, and communication to explore the meeting itself, including pre-meeting activities and post-meeting activities. It provides a comprehensive overview of research in the field and will serve as an invaluable starting point for scholars who seek to understand and improve meetings.
In English, theme/rheme status (or topic/comment) is claimed to be marked by pitch accent type, i.e. L+H⁎ (LH%) versus H⁎ (LL%). Calhoun (2010a) claims that, rather, themes are relatively less prominent than rhemes. The phonetic realisation of themes and rhemes was looked at in a semi-spontaneous game task, e.g. (following Will the banana land on some money?) No, the lollipop (rheme) will land on some money (theme), the banana (theme) will land on a monster (rheme). There were some phonetic differences consistent with an accent type difference: the preceding L pitch elbow, and the H peak, of (L+)H⁎ accents were later and lower on themes than rhemes. Themes also had a high boundary (LH%, HH% or H-) more often. However, these differences were small and not consistent. On the other hand, there were large and consistent differences in the relative prominence of paired themes and rhemes (e.g. lollipop and money). In theme–rheme order, the rheme f0 peak was slightly higher, whereas in rheme–theme order, it was substantially higher. The f0 peaks of paired themes and rhemes were also highly correlated. There were smaller differences in mean intensity and duration. This is clear support for Calhoun's claim that relative prominence marks the theme/rheme distinction, and for the importance of metrical prominence in signalling information structure.
Synchronized verbal behavior can reveal important information about social dynamics. This study introduces the linguistic style matching (LSM) algorithm for calculating verbal mimicry based on an automated textual analysis of function words. The LSM algorithm was applied to language generated during a small group discussion in which 70 groups comprised of 324 individuals engaged in an information search task either face-to-face or via text-based computer-mediated communication. As a metric, LSM predicted the cohesiveness of groups in both communication environments, and it predicted task performance in face-to-face groups. Other language features were also related to the groups’ cohesiveness and performance, including word count, pronoun patterns, and verb tense. The results reveal that this type of automated measure of verbal mimicry can be an objective, efficient, and unobtrusive tool for predicting underlying social dynamics. In total, the study demonstrates the effectiveness of using language to predict change in social psychological factors of interest.
The focus of this paper was twofold: to examine critical team leader behaviors (as perceived by the subordinate) that result in team member satisfaction; and to determine if there is a significant difference between the perceptions of team leaders and team members regarding the level of team satisfaction and factors that predict team leader performance. Results indicate that team member satisfaction was influenced by: the extent to which communication within the group was open; and the team leaders’ performance. Team leader performance was influenced by the team members’ satisfaction with their leaders’ ability to resolve conflicts and the teams’ openness in communication. Team members’ and leaders’ perceptions did not differ significantly regarding open communication in the group, however, team members assessed their leaders’ performance less favorably than the team leaders assessed themselves and were less satisfied with the team leaders’ ability to resolve conflicts.
Given the ubiquity, time investment, and theoretical relevance of meetings to work attitudes, this study explored whether organizational science should consider employee satisfaction with meetings as a contemporary, important, and discrete facet of job satisfaction. Using affective events theory, we postulated that meetings are affect-generating events that meaningfully contribute to overall job satisfaction. Two surveys queried working adults: Study 1 used a paper-based survey (n = 201), while Study 2 used an Internet-based survey (n = 785). Satisfaction with meetings was positively related to and significantly predicted overall job satisfaction (p < .05) after controlling for individual difference variables (e.g., participant background variables, negative affect), traditional job satisfaction facets (e.g., work, supervision, pay), and other conceptually relevant constructs (e.g., satisfaction with communication, organizational commitment). Exploratory (Study 1) and confirmatory (Study 2) factor analyses provided evidence that meeting satisfaction is a distinct facet of job satisfaction. Finally, as hypothesized, the relationship between meeting satisfaction and job satisfaction depends in part upon the number of meetings typically attended. The relationship was stronger (more positive) when meeting demands were higher and weaker when meeting demands were lower. Implications for assessment, leadership development, on-boarding, and high potential initiatives are discussed. ©2010 Wiley Periodicals, Inc.
The ability to understand and manage social signals of a person we are communicating with is the core of social intelligence. Social intelligence is a facet of human intelligence that has been argued to be indispensable and perhaps the most important for success in life. This paper argues that next-generation computing needs to include the essence of social intelligence – the ability to recognize human social signals and social behaviours like turn taking, politeness, and disagreement – in order to become more effective and more efficient. Although each one of us understands the importance of social signals in everyday life situations, and in spite of recent advances in machine analysis of relevant behavioural cues like blinks, smiles, crossed arms, laughter, and similar, design and development of automated systems for social signal processing (SSP) are rather difficult. This paper surveys the past efforts in solving these problems by a computer, it summarizes the relevant findings in social psychology, and it proposes a set of recommendations for enabling the development of the next generation of socially aware computing.
An increasing awareness of the scientific and technological value of the automatic understanding of faceto- face social interaction has motivated in the past few years a surge of interest in the devising of computational techniques for conversational analysis. As an alternative to existing linguistic approaches for the automatic analysis of conversations, a relatively recent domain is using findings in social cognition, social psychology, and communication that have established the key role that nonverbal communication plays in the formation, maintenance, and evolution of a number of fundamental social constructs, which emerge from face-to-face interactions in time scales that range from short glimpses all the way to longterm encounters. Small group conversations are a specific case on which much of this work has been conducted. This paper reviews the existing literature on automatic analysis of small group conversations using nonverbal communication, and aims at bridging the current fragmentation of the work in this domain, currently split among half a dozen technical communities. The review is organized around the main themes studied in the literature and discusses, in a comparative fashion, about 100 works addressing problems related to the computational modeling of interaction management, internal states, personality traits, and social relationships in small group conversations, along with pointers to the relevant literature in social science. Some of the many open challenges and opportunities in this domain are also discussed.
The word "Anna" was spoken by 12 female and 11 male subjects with six different emotional expressions: "rage/hot anger," "despair/lamentation," "contempt/disgust," "joyful surprise," "voluptuous enjoyment/sensual satisfaction," and "affection/tenderness." In an acoustical analysis, 94 parameters were extracted from the speech samples and broken down by correlation analysis to 15 parameters entering subsequent statistical tests. The results show that each emotion can be characterized by a specific acoustic profile, differentiating that emotion significantly from all others. If aversive emotions are tested against hedonistic emotions as a group, it turns out that the best indicator of aversiveness is the ratio of peak frequency (frequency with the highest amplitude) to fundamental frequency, followed by the peak frequency, the percentage of time segments with nonharmonic structure ("noise"), frequency range within single time segments, and time of the maximum of the peak frequency within the utterance. Only the last parameter, however, codes aversiveness independent of the loudness of an utterance.
55 Million: A Fresh Look at the Number Effectiveness and Cost of Meetings in the U
- Elise Keith
Anticipate the User: Multimodal Analyses in Human-Machine Interaction towards Group Interactions
- Ronald Böck
- Böck Ronald
The effect of emotion on voice production and speech acoustics.Ph. D. Dissertation . The University of Western Australia
- T Johnstone
- Johnstone T.