Publications

Abstract

Increasing evidence suggests that interlocutors use visual communicative signals to form predictions about unfolding utterances, but there is little data on the predictive potential of facial signals in conversation. In an online experiment with virtual agents, we examine whether facial signals produced by an addressee may allow speakers to anticipate the response to a question before it is given. Participants (n = 80) viewed videos of short conversation fragments between two virtual humans. Each fragment ended with the Questioner asking a question, followed by a pause during which the Responder looked either straight at the Questioner (baseline), or averted their gaze, or accompanied the straight gaze with one of the following facial signals: brow raise, brow frown, nose wrinkle, smile, squint, mouth corner pulled back (dimpler). Participants then indicated on a 6-point scale whether they expected a “yes” or “no” response. Analyses revealed that all signals received different ratings relative to the baseline: brow raises, dimplers, and smiles were associated with more positive responses, gaze aversions, brow frowns, nose wrinkles, and squints with more negative responses. Qur findings show that interlocutors may form strong associations between facial signals and upcoming responses to questions, highlighting their predictive potential in face-to-face conversation.

Abstract

Repair is a core building block of human communication, allowing us to address problems of understanding in conversation. Past research has uncovered the basic mechanisms by which interactants signal and solve such problems. However, the focus has been on verbal interaction, neglecting the fact that human communication is inherently multimodal. Here, we focus on a visual signal particularly prevalent in signalling problems of understanding: eyebrow furrows and raises. We present, first, a corpus study showing that differences in eyebrow actions (furrows versus raises) were systematically associated with differences in the format of verbal repair initiations. Second, we present a follow-up study using an avatar that allowed us to test the causal consequences of addressee eyebrow movements, zooming into the effect of eyebrow furrows as signals of trouble in understanding in particular. The results revealed that addressees’ eyebrow furrows have a striking effect on speakers’ speech, leading speakers to produce answers to questions several seconds longer than when not perceiving addressee eyebrow furrows while speaking. Together, the findings demonstrate that eyebrow movements play a communicative role in initiating repair during conversation rather than being merely epiphenomenal and that their occurrence can critically influence linguistic behaviour. Thus, eyebrow movements should be considered core coordination devices in human conversational interaction.

Abstract

In face-to-face conversation, people use speech and gesture to convey meaning. Seeing gestures alongside speech facilitates comprehenders’ language processing, but crucially, the mechanisms underlying this facilitation remain unclear. We investigated whether comprehenders use the semantic information in gestures, typically preceding related speech, to predict upcoming meaning. Dutch adults listened to questions asked by a virtual avatar. Questions were accompanied by an iconic gesture (e.g., typing) or meaningless control movement (e.g., arm scratch) followed by a short pause and target word (e.g., “type”). A Cloze experiment showed that gestures improved explicit predictions of upcoming target words. Moreover, an EEG experiment showed that gestures reduced alpha and beta power during the pause, indicating anticipation, and reduced N400 amplitudes, demonstrating facilitated semantic processing. Thus, comprehenders use iconic gestures to predict upcoming meaning. Theories of linguistic prediction should incorporate communicative bodily signals as predictive cues to capture how language is processed in face-to-face interaction.

Abstract

Despite the importance of greetings for opening social interactions, their multimodal coordination processes remain poorly understood. We used a naturalistic, lab-based setup where pairs of unacquainted participants approached and greeted each other while unaware their greeting behavior was studied. We measured the prevalence and time course of multimodal behaviors potentially culminating in a handshake, including motor behaviors (e.g., walking, standing up, hand movements like raise, grasp, and retraction), gaze patterns (using eye tracking glasses), and speech (close and distant verbal salutations). We further manipulated the visibility of partners’ eyes to test its effect on gaze. Our findings reveal that gaze to a partner's face increases over the course of a greeting, but is partly averted during approach and is influenced by the visibility of partners’ eyes. Gaze helps coordinate handshakes, by signaling intent and guiding the grasp. The timing of adjacency pairs in verbal salutations is comparable to the precision of floor transitions in the main body of conversations, and varies according to greeting phase, with distant salutation pair parts featuring more gaps and close salutation pair parts featuring more overlap. Gender composition and a range of multimodal behaviors affect whether pairs chose to shake hands or not. These findings fill several gaps in our understanding of greetings and provide avenues for future research, including advancements in social robotics and human−robot interaction.

Abstract

During conversation, speakers coordinate and synergize their behaviors at multiple levels, and in different ways. The extent to which individuals converge or diverge in their behaviors during interaction may relate to interpersonal differences relevant to social interaction, such as empathy as measured by the empathy quotient (EQ). An association between interpersonal difference in empathy and interpersonal entrainment could help to throw light on how interlocutor characteristics influence interpersonal entrainment. We investigated this possibility in a corpus of unconstrained conversation between dyads. We used dynamic time warping to quantify entrainment between interlocutors of head motion, hand motion, and maximum speech f0 during question–response sequences. We additionally calculated interlocutor differences in EQ scores. We found that, for both head and hand motion, greater difference in EQ was associated with higher entrainment. Thus, we consider that people who are dissimilar in EQ may need to “ground” their interaction with low-level movement entrainment. There was no significant relationship between f0 entrainment and EQ score differences.

Abstract

When engaged in spoken conversation, speakers convey meaning using both speech and visual signals, such as facial expressions and manual gestures. An important question is how information is distributed in utterances during face-to-face interaction when information from visual signals is also present. In a corpus of casual Dutch face-to-face conversations, we focus on spoken questions in particular because they occur frequently, thus constituting core building blocks of conversation. We quantified information density (i.e. lexical entropy and surprisal) and the number and relative duration of facial and manual signals. We tested whether lexical information density or the number of visual signals differed between the first and last halves of questions, as well as whether the number of visual signals occurring in the less-predictable portion of a question was associated with the lexical information density of the same portion of the question in a systematic manner. We found that information density, as well as number of visual signals, were higher in the first half of questions, and specifically lexical entropy was associated with fewer, but longer visual signals. The multimodal front-loading of questions and the complementary distribution of visual signals and high entropy words in Dutch casual face-to-face conversations may have implications for the parallel processes of utterance comprehension and response planning during turn-taking.

Abstract

Conversation requires a substantial amount of coordination between dialogue participants, from managing turn taking to negotiating mutual understanding. Part of this coordination effort surfaces as the reuse of linguistic behaviour across speakers, a process often referred to as alignment. While the presence of linguistic alignment is well documented in the literature, several questions remain open, including the extent to which patterns of reuse across speakers have an impact on the emergence of labelling conventions for novel referents. In this study, we put forward a methodology for automatically detecting shared lemmatised constructions---expressions with a common lexical core used by both speakers within a dialogue---and apply it to a referential communication corpus where participants aim to identify novel objects for which no established labels exist. Our analyses uncover the usage patterns of shared constructions in interaction and reveal that features such as their frequency and the amount of different constructions used for a referent are associated with the degree of object labelling convergence the participants exhibit after social interaction. More generally, the present study shows that automatically detected shared constructions offer a useful level of analysis to investigate the dynamics of reference negotiation in dialogue.

Abstract

Gestures are integral components of face-to-face communication. They unfold over time, often following predictable movement phases of preparation, stroke, and re-
traction. Yet, the prevalent approach to automatic gesture detection treats the problem as binary classification, classifying a segment as either containing a gesture or not, thus failing to capture its inherently sequential and contextual nature. To address this, we introduce a novel framework that reframes the task as a multi-phase sequence labeling problem rather than binary classification. Our model processes sequences of skeletal movements over time windows, uses Transformer encoders to learn contextual embeddings, and leverages Conditional Random Fields to perform sequence labeling. We evaluate our proposal on a large dataset of diverse co-speech gestures in task-oriented face-to-face dialogues. The results consistently demonstrate that our method significantly outperforms strong baseline models in detecting gesture strokes. Furthermore, applying Transformer encoders to learn contextual embeddings from movement sequences substantially improves gesture unit detection. These results highlight our framework’s capacity to capture the fine-grained dynamics of co-speech gesture phases, paving the way for more nuanced and accurate gesture detection and analysis.

Abstract

In face-to-face dialogues, the form-meaning relationship of co-speech gestures varies depending on contextual factors such as what the gestures refer to and the individual characteristics of speakers. These factors make co-speech gesture representation learning challenging. How can we learn meaningful gestures representations considering gestures’ variability and relationship with speech? This paper tackles this challenge by employing self-supervised contrastive learning techniques to learn gesture representations from skeletal and speech information. We propose an approach that includes both unimodal and multimodal pre-training to ground gesture representations in co-occurring speech. For training, we utilize a face-to-face dialogue dataset rich with representational iconic gestures. We conduct thorough intrinsic evaluations of the learned representations through comparison with human-annotated pairwise gesture similarity. Moreover, we perform a diagnostic probing analysis to assess the possibility of recovering interpretable gesture features from the learned representations. Our results show a significant positive correlation with human-annotated gesture similarity and reveal that the similarity between the learned representations is consistent with well-motivated patterns related to the dynamics of dialogue interaction. Moreover, our findings demonstrate that several features concerning the form of gestures can be recovered from the latent representations. Overall, this study shows that multimodal contrastive learning is a promising approach for learning gesture representations, which opens the door to using such representations in larger-scale gesture analysis studies.

Abstract

Purpose

To perform a scoping review to investigate the psychosocial impact of having an altered facial expression in five neurological diseases.
Methods

A systematic literature search was performed. Studies were on Bell’s palsy, facioscapulohumeral muscular dystrophy (FSHD), Moebius syndrome, myotonic dystrophy type 1, or Parkinson’s disease patients; had a focus on altered facial expression; and had any form of psychosocial outcome measure. Data extraction focused on psychosocial outcomes.
Results

Bell’s palsy, myotonic dystrophy type 1, and Parkinson’s disease patients more often experienced some degree of psychosocial distress than healthy controls. In FSHD, facial weakness negatively influenced communication and was experienced as a burden. The psychosocial distress applied especially to women (Bell’s palsy and Parkinson’s disease), and patients with more severely altered facial expression (Bell’s palsy), but not for Moebius syndrome patients. Furthermore, Parkinson’s disease patients with more pronounced hypomimia were perceived more negatively by observers. Various strategies were reported to compensate for altered facial expression.
Conclusions

This review showed that patients with altered facial expression in four of five included neurological diseases had reduced psychosocial functioning. Future research recommendations include studies on observers’ judgements of patients during social interactions and on the effectiveness of compensation strategies in enhancing psychosocial functioning.
Implications for rehabilitation

Negative effects of altered facial expression on psychosocial functioning are common and more abundant in women and in more severely affected patients with various neurological disorders.

Health care professionals should be alert to psychosocial distress in patients with altered facial expression.

Learning of compensatory strategies could be a beneficial therapy for patients with psychosocial distress due to an altered facial expression.

Abstract

During face-to-face conversation, transitions between speaker turns are incredibly fast. These fast turn exchanges seem to involve next speakers predicting upcoming semantic information, such that next turn planning can begin before a current turn is complete. Given that face-to-face conversation also involves the use of communicative bodily signals, an important question is how bodily signals such as co-speech hand gestures play into these processes of prediction and fast responding. In this corpus study, we found that hand gestures that depict or refer to semantic information started before the corresponding information in speech, which held both for the onset of the gesture as a whole, as well as the onset of the stroke (the most meaningful part of the gesture). This early timing potentially allows listeners to use the gestural information to predict the corresponding semantic information to be conveyed in speech. Moreover, we provided further evidence that questions with gestures got faster responses than questions without gestures. However, we found no evidence for the idea that how much a gesture precedes its lexical affiliate (i.e., its predictive potential) relates to how fast responses were given. The findings presented here highlight the importance of the temporal relation between speech and gesture and help to illuminate the potential mechanisms underpinning multimodal language processing during face-to-face conversation.

Abstract

Most language use occurs in face-to-face conversation, which involves rapid turn-taking. Seeing communicative bodily signals in addition to hearing speech may facilitate such fast responding. We tested whether this holds for co-speech hand gestures by investigating whether these gestures speed up button press responses to questions. Sixty native speakers of Dutch viewed videos in which an actress asked yes/no-questions, either with or without a corresponding iconic hand gesture. Participants answered the questions as quickly and accurately as possible via button press. Gestures did not impact response accuracy, but crucially, gestures sped up responses, suggesting that response planning may be finished earlier when gestures are seen. How much gestures sped up responses was not related to their timing in the question or their timing with respect to the corresponding information in speech. Overall, these results are in line with the idea that multimodality may facilitate fast responding during face-to-face conversation.

Abstract

The typical pattern of alternating turns in conversation seems trivial at first sight. But a closer look quickly reveals the cognitive challenges involved, with much of it resulting from the fast-paced nature of conversation. One core ingredient to turn coordination is the anticipation of upcoming turn ends so as to be able to ready oneself for providing the next contribution. Across two experiments, we investigated two variables inherent to face-to-face conversation, the presence of visual bodily signals and preceding discourse context, in terms of their contribution to turn end anticipation. In a reaction time paradigm, participants anticipated conversational turn ends better when seeing the speaker and their visual bodily signals than when they did not, especially so for longer turns. Likewise, participants were better able to anticipate turn ends when they had access to the preceding discourse context than when they did not, and especially so for longer turns. Critically, the two variables did not interact, showing that visual bodily signals retain their influence even in the context of preceding discourse. In a pre-registered follow-up experiment, we manipulated the visibility of the speaker's head, eyes and upper body (i.e. torso + arms). Participants were better able to anticipate turn ends when the speaker's upper body was visible, suggesting a role for manual gestures in turn end anticipation. Together, these findings show that seeing the speaker during conversation may critically facilitate turn coordination in interaction.

Abstract

Human language is extremely versatile, combining a limited set of signals in an unlimited number of ways. However, it is unknown whether conversational visual signals feed into the composite utterances with which speakers communicate their intentions. We assessed whether different combinations of visual signals lead to different intent interpretations of the same spoken utterance. Participants viewed a virtual avatar uttering spoken questions while producing single visual signals (i.e., head turn, head tilt, eyebrow raise) or combinations of these signals. After each video, participants classified the communicative intention behind the question. We found that composite utterances combining several visual signals conveyed different meaning compared to utterances accompanied by the single visual signals. However, responses to combinations of signals were more similar to the responses to related, rather than unrelated, individual signals, indicating a consistent influence of the individual visual signals on the whole. This study therefore provides first evidence for compositional, non-additive (i.e., Gestalt-like) perception of multimodal language.

Abstract

The natural ecology of language is conversation, with individuals taking turns speaking to communicate in a back-and-forth fashion. Language in this context involves strings of words that a listener must process while simultaneously planning their own next utterance. It would thus be highly advantageous if language users distributed information within an utterance in a way that may facilitate this processing–planning dynamic. While some studies have investigated how information is distributed at the level of single words or clauses, or in written language, little is known about how information is distributed within spoken utterances produced during naturalistic conversation. It also is not known how information distribution patterns of spoken utterances may differ across languages. We used a set of matched corpora (CallHome) containing 898 telephone conversations conducted in six different languages (Arabic, English, German, Japanese, Mandarin, and Spanish), analyzing more than 58,000 utterances, to assess whether there is evidence of distinct patterns of information distributions at the utterance level, and whether these patterns are similar or differed across the languages. We found that English, Spanish, and Mandarin typically show a back-loaded distribution, with higher information (i.e., surprisal) in the last half of utterances compared with the first half, while Arabic, German, and Japanese showed front-loaded distributions, with higher information in the first half compared with the last half. Additional analyses suggest that these patterns may be related to word order and rate of noun and verb usage. We additionally found that back-loaded languages have longer turn transition times (i.e.,time between speaker turns)

Abstract

Recipients process information from speech and co-speech gestures, but it is currently unknown how this processing is influenced by the presence of other important social cues, especially gaze direction, a marker of communicative intent. Such cues may modulate neural activity in regions associated either with the processing of ostensive cues, such as eye gaze, or with the processing of semantic information, provided by speech and gesture.
Participants were scanned (fMRI) while taking part in triadic communication involving two recipients and a speaker. The speaker uttered sentences that
were and were not accompanied by complementary iconic gestures. Crucially, the speaker alternated her gaze direction, thus creating two recipient roles: addressed (direct gaze) vs unaddressed (averted gaze) recipient. The comprehension of Speech&Gesture relative to SpeechOnly utterances recruited middle occipital, middle temporal and inferior frontal gyri, bilaterally. The calcarine sulcus and posterior cingulate cortex were sensitive to differences between direct and averted gaze. Most importantly, Speech&Gesture utterances, but not SpeechOnly utterances, produced additional activity in the right middle temporal gyrus when participants were addressed. Marking communicative intent with gaze direction modulates the processing of speech–gesture utterances in cerebral areas typically associated with the semantic processing of multi-modal communicative acts.

Abstract

One of the most intriguing aspects of human communication is its turn-taking system. It requires the ability to process on-going turns at talk while planning the next, and to launch this next turn without considerable overlap or delay. Recent research has investigated the eye movements of observers of dialogues to gain insight into how we process turns at talk. More specifically, this research has focused on the extent to which we are able to anticipate the end of current and the beginning of next turns. At the same time, there has been a call for shifting experimental paradigms exploring social-cognitive processes away from passive observation towards online processing. Here, we present research that responds to this call by situating state-of-the-art technology for tracking interlocutors’ eye movements within spontaneous, face-to-face conversation. Each conversation involved three native speakers of English. The analysis focused on question-response sequences involving just two of those participants, thus rendering the third momentarily unaddressed. Temporal analyses of the unaddressed participants’ gaze shifts from current to next speaker revealed that unaddressed participants are able to anticipate next turns, and moreover, that they often shift their gaze towards the next speaker before the current turn ends. However, an analysis of the complex structure of turns at talk revealed that the planning of these gaze shifts virtually coincides with the points at which the turns first become recog-nizable as possibly complete. We argue that the timing of these eye movements is governed by an organizational principle whereby unaddressed participants shift their gaze at a point that appears interactionally most optimal: It provides unaddressed participants with access to much of the visual, bodily behavior that accompanies both the current speaker’s and the next speaker’s turn, and it allows them to display recipiency with regard to both speakers’ turns.

Abstract

Hand gestures and speech form a single integrated system of meaning during language comprehension, but is gesture processed with speech in a unique fashion? We had subjects watch multimodal videos that presented auditory (words) and visual (gestures and actions on objects) information. Half of the subjects related the audio information to a written prime presented before the video, and the other half related the visual information to the written prime. For half of the multimodal video stimuli, the audio and visual information contents were congruent, and for the other half, they were incongruent. For all subjects, stimuli in which the gestures and actions were incongruent with the speech produced more errors and longer response times than did stimuli that were congruent, but this effect was less prominent for speech-action stimuli than for speech-gesture stimuli. However, subjects focusing on visual targets were more accurate when processing actions than gestures. These results suggest that although actions may be easier to process than gestures, gestures may be more tightly tied to the processing of accompanying speech.

Abstract

In everyday human communication, we often express our communicative intentions by manually pointing out referents in the material world around us to an addressee, often in tight synchronization with referential speech. This study investigated whether and how the kinematic form of index finger pointing gestures is shaped by the gesturer's communicative intentions and how this is modulated by the presence of concurrently produced speech. Furthermore, we explored the neural mechanisms underpinning the planning of communicative pointing gestures and speech. Two experiments were carried out in which participants pointed at referents for an addressee while the informativeness of their gestures and speech was varied. Kinematic and electrophysiological data were recorded online. It was found that participants prolonged the duration of the stroke and poststroke hold phase of their gesture to be more communicative, in particular when the gesture was carrying the main informational burden in their multimodal utterance. Frontal and P300 effects in the ERPs suggested the importance of intentional and modality-independent attentional mechanisms during the planning phase of informative pointing gestures. These findings contribute to a better understanding of the complex interplay between action, attention, intention, and language in the production of pointing gestures, a communicative act core to human interaction.

Abstract

Despite the importance of effective pain communication, talking about pain represents a major challenge for patients and clinicians because pain is a private and subjective experience. Focusing primarily on acute pain, this article considers the limitations of current methods of obtaining information about the sensory characteristics of pain and suggests that spontaneously produced “co-speech hand gestures” may constitute an important source of information here. Although this is a relatively new area of research, we present recent empirical evidence that reveals that co-speech gestures contain important information about pain that can both add to and clarify speech. Following this, we discuss how these findings might eventually lead to a greater understanding of the sensory characteristics of pain, and to improvements in treatment and support for pain sufferers. We hope that this article will stimulate further research and discussion of this previously overlooked dimension of pain communication

Abstract

Speakers can adapt their speech and co-speech gestures for
addressees. Here, we investigate whether this ability is
modulated by age. Younger and older adults participated in a
comic narration task in which one participant (the speaker)
narrated six short comic stories to another participant (the
addressee). One half of each story was known to both participants, the other half only to the speaker. Younger but
not older speakers used more words and gestures when narrating novel story content as opposed to known content.
We discuss cognitive and pragmatic explanations of these findings and relate them to theories of gesture production.