Multiparty Interactions Research Articles

Active Learning Based Constrained Clustering For Speaker Diarization

Most speaker diarization research has focused on unsupervised scenarios, where no human supervision is available. However, in many real-world applications, a certain amount of human input could be expected, especially when minimal human supervision brings significant performance improvement. In this study, we propose an active learning based bottom-up speaker clustering algorithm to effectively improve speaker diarization performance with limited human input. Specifically, the proposed active learning based speaker clustering has two different stages: explore and constrained clustering. The explore stage is to quickly discover at least one sample for each speaker for boosting speaker clustering process with reliable initial speaker clusters. After discovering all, or a majority, of the involved speakers during explore stage, the constrained clustering is performed. Constrained clustering is similar to traditional bottom-up clustering process with an important difference that the clusters created during explore stage are restricted from merging with each other. Constrained clustering continues until only the clusters generated from the explore stage are left. Since the objective of active learning based speaker clustering algorithm is to provide good initial speaker models, performance saturates as soon as sufficient examples are ensured for each cluster. To further improve diarization performance with increasing human input, we propose a second method which actively select speech segments that account for the largest expected speaker error from existing cluster assignments for human evaluation and reassignment. The algorithms are evaluated on our recently created Apollo Mission Control Center dataset as well as augmented multiparty interaction meeting corpus. The results indicate that the proposed active learning algorithms are able to reduce diarization error rate significantly with a relatively small amount of human supervision.

Value creation and appropriation in product returns management

PurposeProduct returns management (PRM) is a core supply chain management process. Though the importance of value creation and appropriation is acknowledged, extant studies on value in product returns tend to be limited to the residual asset value (cost recovery) of the returned products. Further, value discussion in PRM is limited to the value implications for a single party in the returns transaction rather than all the product returns chain entities. The purpose of this paper is to explore value creation and appropriation in a triad of supplier-retailer-3PL in the product returns chain.Design/methodology/approachThe study uses an inductive qualitative approach. Semi-structured interviews with executives in a triad of organisations formed the primary data source for the study.FindingsThe paper identifies six value drivers and develops a value creation and appropriation framework. It shows that facilitation, value orientation, process alignment and relational factors are key drivers of value creation and appropriation in PRM.Research limitations/implicationsThe findings reinforce the view that value creation and appropriation are the outcomes of multi-party interactions in a product return chain. The framework presented contributes to the literature by showing the linkages amongst key drivers.Practical implicationsThe findings show the important role of external process facilitation and how a 3PL contributes to value creation in a triadic relationship.Originality/valueResearch based on a triadic product returns chain is a unique dimension of this study.

COPING WITH L2 SOCIOPRAGMATIC SENSITIVITY USING A STORY-BASED APPROACH

Abstract : Previous research findings have led to a gap that sociopragmatic failure, instead of pragmalinguistic failure, has scarcely been resolved despite its crucial function in communication. Therefore, this paper proposes a story-based approach, particularly a joint storytelling with multi-party interaction, to deal with learners’ L2 sociopragmatic sensitivity. EFL learners with diverse cultural backgrounds need a motivating environment with agents that can co-construct experiences for optimum learning. By telling stories, learners are engaged in social relations that set them into interpersonal interaction demanding sociopragmatic awareness necessary for the development of their L2 sociopragmatic competence. For this purpose, classroom implementation follows the dimensions of embeddedness, tellership, and tellability while the learning sequence is based on co-constructed learning principles with four stages: setting the stage, executing the storytelling, monitoring the process, and evaluating the results. Future research may be conducted to test the compatibility of the model with actual EFL classroom instructions. permalink/DOI: dx.doi.org/10.17977/um015v45i22017p108

Managing complaints in multilingual care encounters

AbstractTroubles-telling and complaints are common in contexts of care for older people and need to be managed by care staff in a respectful manner. This paper examines the handling of an older person’s complaints in multilingual care encounters that involve participants who do not share a common language. The data consist of video-recordings and ethnographic fieldwork in a residential home for older people in Sweden that is characterised by a variety of languages and backgrounds. The findings are based on analyses of multi-party interactions involving an Arabic-speaking resident and caregivers with different levels of knowledge in different languages. We focus on complaint sequences when the resident expresses a negative stance (displeasure, anger, etc.) towards some difficult circumstance. Using the methodology of conversation analysis, we analyse the affect-regulating work through which the caregivers attempt to turn a pressing situation into a moment of cheerfulness and intimacy. The analyses bring to light the multilingual practices that the caregivers draw upon in pursuing this work, such as translating and giving voice to the resident’s complaining.

Generation of Bystander Robot Actions Based on Analysis of Relative Probability of Human Actions

This paper describes a method of rule extraction for generation of appropriate actions by a robot in a multiparty conversation based on the relative probability of human actions in a similar situation. The proposed method was applied to a dataset collected from multiparty interactions between two robots and one human subject who took on the role of supporting one robot. By computing the relative occurrence probabilities of human actions after the execution of the robots’ actions, twenty rules describing human behavior in such a role were identified. To evaluate the rules, the human role was filled by a new bystander robot and other subjects were asked to report their impressions of video clips in which the bystander robot acted or did not act in accordance with the rules. The reported impressions and a quantitative analysis of the rules suggest that the behavior of listening and the supporting role that the subjects play can be reproduced by a bystander robot acting in accordance with the rules identified by the proposed method.

Expanding or postponing? Patterns of negotiation in multi-party interactions in social work

In this article, we examine patterns of negotiation in multi-party decision making in social work. We draw on Strauss’ theory of negotiated order and a discourse analytical approach, seeking to gain insight into the complex accomplishment of making a decision in an inter-professional and multi-party setting. Working with data from 97 team meetings in a social work setting, we identify two patterns of negotiation in talk: expanding and postponing. ‘Expanding’ covers a group of interactional actions involving turn-taking and closure, while ‘postponing’ includes a group of actions whereby assessments or topics are avoided or made irrelevant. Both are examples of the complex ways in which team members negotiate both the institutional order and the decision to be made in the specific case in situ.

Augmenting Multi-Party Face-to-Face Interactions Amongst Strangers with User Generated Content

We present the results of an investigation into the role of curated representations of self, which we term Digital Selfs, in augmented multi-party face-to-face interactions. Advancements in wearable technologies (such as Head-Mounted Displays) have renewed interest in augmenting face-to-face interaction with digital content. However, existing work focuses on algorithmic matching between users, based on data-mining shared interests from individuals’ social media accounts, which can cause information that might be inappropriate or irrelevant to be disclosed to others. An alternative approach is to allow users to manually curate the digital augmentation they wish to present to others, allowing users to present those aspects of self that are most important to them and avoid undesired disclosure. Through interviews, video analysis, questionnaires and device logging, of 23 participants in 6 multi-party gatherings where individuals were allowed to freely mix, we identified how users created Digital Selfs from media largely outside existing social media accounts, and how Digital Selfs presented through HMDs were employed in multi-party interactions, playing key roles in facilitating strangers to interact with each other. We present guidance for the design of future multi-party digital augmentations in collaborative scenarios.

多人数インタラクションの多様性とダイナミズム : 多人数インタラクションでは何が多くなるのか?(第18回研究大会ワークショップ)

多人数インタラクションの多様性とダイナミズム : 多人数インタラクションでは何が多くなるのか?(第18回研究大会ワークショップ)

Concurrency-preserving and sound monitoring of multi-threaded component-based systems: theory, algorithms, implementation, and evaluation

Abstract This paper addresses the monitoring of logic-independent linear-time user-provided properties in multi-threaded component-based systems. We consider intrinsically independent components that can be executed concurrently with a centralized coordination for multiparty interactions. In this context, the problem that arises is that a global state of the system is not available to the monitor. A naive solution to this problem would be to plug in a monitor which would force the system to synchronize in order to obtain the sequence of global states at runtime. Such a solution would defeat the whole purpose of having concurrent components. Instead, we reconstruct on-the-fly the global states by accumulating the partial states traversed by the system at runtime. We define transformations of components that preserve their semantics and concurrency and, at the same time, allow to monitor global-state properties. Moreover, we present RVMT-BIP, a prototype tool implementing the transformations for monitoring multi-threaded systems described in the Behavior, Interaction, Priority (BIP) framework, an expressive framework for the formal construction of heterogeneous systems. Our experiments on several multi-threaded BIP systems show that RVMT-BIP induces a cheap runtime overhead.

Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion.

Speaker diarization consists of assigning speech signals to people engaged in a dialogue. An audio-visual spatiotemporal diarization model is proposed. The model is well suited for challenging scenarios that consist of several participants engaged in multi-party interaction while they move around and turn their heads towards the other participants rather than facing the cameras and the microphones. Multiple-person visual tracking is combined with multiple speech-source localization in order to tackle the speech-to-person association problem. The latter is solved within a novel audio-visual fusion method on the following grounds: binaural spectral features are first extracted from a microphone pair, then a supervised audio-visual alignment technique maps these features onto an image, and finally a semi-supervised clustering method assigns binaural spectral features to visible persons. The main advantage of this method over previous work is that it processes in a principled way speech signals uttered simultaneously by multiple persons. The diarization itself is cast into a latent-variable temporal graphical model that infers speaker identities and speech turns, based on the output of an audio-visual association process, executed at each time slice, and on the dynamics of the diarization variable itself. The proposed formulation yields an efficient exact inference procedure. A novel dataset, that contains audio-visual training data as well as a number of scenarios involving several participants engaged in formal and informal dialogue, is introduced. The proposed method is thoroughly tested and benchmarked with respect to several state-of-the art diarization algorithms.

Modeling the synchrony between interacting people: application to role recognition

The study of social interactions has attracted increasing attentions. The role recognition is one of its possible applications and the core of this study. This article proposes some approaches to automatically recognize the role of the participants of a meeting by modeling the synchrony of temporal nonverbal audio features. In our approache the Influence Model (IM), a Hidden Markov Model (HMM)-like, is used to model this synchrony and to extract from input data a feature vector that contains both information about temporal transitions (intra-personal data) and interaction between participants (inter-personal data). This modeling of the meeting is used as input of a Random Forests (RFs) for the role recognition task. The experiments are performed on 138 meetings (approximately 45 hours of recordings) from Augmented Multiparty Interaction (AMI) Corpus. Accuracy scores show that this combination of generative (IM) and discriminative (RFs) approaches permits to outperform state-of-the-art role recognition rates.

Speaker Diarization and Linking of Meeting Data

Finding who spoke when in a collection of recordings, with speakers being uniquely identified across the database, is a challenging task. In this scenario, reasonable computing times and acoustic variation across recordings remain two major concerns to address in state-of-the-art speaker diarization systems. This paper extends prior work on diarizing large speech datasets using algorithms that scale well with increasing amounts of data while compensating for across-recording variability. We follow a two-stage approach performing speaker diarization and speaker linking, the former focusing on local within-recording speaker changes and the latter focusing on global speaker changes across the database. In this study, we explore how these two modules interact with each other, while proposing a diarization fusion approach that prevents diarization errors from propagating to the linking stage. We further explore the diarization fusion for speaker linking using different linking strategies and speaker modeling variants. Evaluation is performed on single distant microphone data from the augmented multiparty interaction corpus show the effectiveness of the fusion approach after speaker linking and intersession variability modeling via joint factor analysis.

Collaboration, trouble and repair in multiparty interactions involving couples with dementia or aphasia

Purpose: The aim of the present study was to identify problems with communication with persons with aphasia and persons with dementia in a collaborative interview setting with their significant others. In particular, to compare interactional practices used in order to resolve problems caused by specific symptoms.Method: Five persons with aphasia and five persons with dementia and their spouses participated in the study. Interviews were carried out couple by couple, and the interviews had a task-oriented character. The interviews were video and audio recorded. All interviews were transcribed. From the transcriptions categorisations according to previous literature were made.Result: The results demonstrated that repair sequences were frequent in interaction involving people with aphasia (PWA), and even more so in interaction involving persons with dementia (PWD). In general, it was the PWA/PWD that initiated the repair sequence more often than the spouse, thus keeping the general rule of a preference for self-initiated repair compared to other-initiated repair.Conclusion: The active involvement of the conversational partners in trouble solving sequences in interaction with PWA/PWD demonstrated in the present study indicates that the interactional style of the conversational partner to PWA/PWD important. This implies that conversation partner training programmes would be useful both for PWA and for PWD.

Supporting a child with multiple disabilities to participate in social interaction: The case of asking a question

ABSTRACTAsking a question can be a highly challenging task for a person with multiple disabilities, but questions have not received much attention in research on augmentative and alternative communication (AAC). Conversation analysis is employed to examine an instance of multiparty interaction where a speech and language therapist supports a child with multiple disabilities to ask a question with a communication board. The question is accomplished through a practice where the action is built as a trajectory of interactional steps. Each step is built using ways of involvement that establish different participation spaces designed to deal with different aspects of asking a question: agreeing on the action type, the speaker and recipient, the content of the question, and then asking the question. The segmentation of a question into discrete steps and participation spaces can be used in intervention to model the construction of a question for AAC users and significant others.

The interactional history of examples and parentheses

In this article, we set out to examine how participants organize their note-taking while engaged in multiparty interaction. We first describe the collective display of affiliation as an interactional practice that allows note-takers to identify recordables and to legitimize their writing. We then focus on the use of examples (e.g.) and parentheses in the written notes. While style guides recommend the use of examples and parentheses to indicate subsidiary information, we describe the interactional history that leads to such scriptorial practices in collaborative writing. The analyses show that both examples and parentheses may originate from various interactional practices (e.g. listing, instruction, epistemic disputes) and that they may relate to highly salient topics of the interaction. We use the methods developed in conversation analysis, which we extend to the analysis of multimodal phenomena of interaction.

Dynamic role authorization in multiparty conversations

Abstract Protocols in distributed settings usually rely on the interaction of several parties and often identify the roles involved in communications. Roles may have a behavioral interpretation, as they do not necessarily correspond to sites or physical devices. Notions of role authorization thus become necessary to consider settings in which, e.g., different sites may be authorized to act on behalf of a single role, or in which one site may be authorized to act on behalf of different roles. This flexibility must be equipped with ways of controlling the roles that the different parties are authorized to represent, including the challenging case in which role authorizations are determined only at runtime. We present a typed framework for the analysis of multiparty interaction with dynamic role authorization and delegation. Building on previous work on conversation types with role assignment, our formal model is based on an extension of the π -calculus in which the basic resources are pairs channel-role, which denote the access right of interacting along a given channel representing the given role. To specify dynamic authorization control, our process model includes (1) a novel scoping construct for authorization domains, and (2) communication primitives for authorizations, which allow to pass around authorizations to act on a given channel. An authorization error then corresponds to an action involving a channel and a role not enclosed by an appropriate authorization scope. We introduce a typing discipline that ensures that processes never reduce to authorization errors, including when parties dynamically acquire authorizations.

Multiparty Asynchronous Session Types

Communication is a central elements in software development. As a potential typed foundation for structured communication-centered programming, session types have been studied over the past decade for a wide range of process calculi and programming languages, focusing on binary (two-party) sessions. This work extends the foregoing theories of binary session types to multiparty, asynchronous sessions, which often arise in practical communication-centered applications. Presented as a typed calculus for mobile processes, the theory introduces a new notion of types in which interactions involving multiple peers are directly abstracted as a global scenario. Global types retain the friendly type syntax of binary session types while specifying dependencies and capturing complex causal chains of multiparty asynchronous interactions. A global type plays the role of a shared agreement among communication peers and is used as a basis of efficient type-checking through its projection onto individual peers. The fundamental properties of the session type discipline, such as communication safety, progress, and session fidelity, are established for general n-party asynchronous interactions.

Acquiring pragmatics by Sandrine Zufferey (review)

Reviewed by: Acquiring pragmatics by Sandrine Zufferey Elly Ifantidou Acquiring pragmatics. By Sandrine Zufferey. London: Routledge, 2015. Pp. 202. ISBN 9780415746441. $49.95. Zufferey’s book is organized in five parts that cover pragmatics from its theoretical foundations to its mutual influence with language acquisition (Part 1), social skills (Part 2), and cognitive competencies required in acquiring pragmatic skills (Part 3). Pragmatic development in a second language and autism are examined, too (Part 4). Ten chapters, two under each part, discuss topics such as speech acts, the role of social relations and cultural norms in children’s pragmatic development, metaphor, irony, scalar implicatures, referring expressions, and connectives. Z focuses on cognitive underpinnings on par with social interaction skills; she sidesteps early communicative abilities observed in conversational turn-taking and preschoolers’ situated activities (see Slobin et al. 1996, Matthews 2014). Nevertheless, the book accomplishes the much-awaited unification of the major trends in the pragmatic development of children, that is, the social and the cognitive. Ch. 1 traces popular topics within pragmatic theory back to their origins, namely speech-act theory and H. Paul Grice. This chapter can be a useful review for students who have had semantics and pragmatics courses and are familiar with the standardization hypothesis, nonliteral language in the Gricean framework, and generalized, particularized, and conventional implicatures. It is surprising that the introductory chapter to developmental pragmatics circumvents research on modality, spatial and evidential concepts (see Papafragou 1998, Matsui & Fitneva 2009, Quinn, Doran, & Papafragou 2011, Johanson & Papafragou 2014), and metaphor (see Vosniadou 1989, Pouscoulous 2011, 2014) by drawing on textbooks instead. Other areas where further qualifications are perhaps needed are Herbert Clark’s principle of contrast, intention reading, and cultural learning that have been used to discuss the role of theory of mind (ToM) abilities (e.g. joint [End Page 228] attention, gaze direction, intentional behavior) and social interaction in word learning. Part 1 concludes with an overview of explicit and implicit measures used to assess children’s production and comprehension. Ch. 3 is on the acquisition of speech acts. Emphasis is on effects of age and order of acquisition, direct vs. indirect speech acts, and the use of conventional linguistic forms to convey indirect speech acts. Z introduces evidence on requests and promises, which argues that awareness of conventional rules (in the form of felicity conditions) and level of implicitness do not explain children’s early ability to produce and understand direct and indirect requests. Instead, the data suggest that complexity of syntactic structures and of inferences that are required to retrieve the intended meaning can explain why young children understand indirect requests that tap into their developing ToM abilities better than indirect requests that rely on world knowledge they have not yet acquired. Ch. 4 offers a comprehensive review of pragmatic competencies tapping into social behavior and cognitive growth. Z illustrates three- to four-year-old children’s ability to adapt tone of voice, to shift from direct to indirect speech acts, and to add politeness markers depending on the social status of addressees and the context of conversation. She stresses the role of multiparty peer interaction in situations of conflict where discourse markers are used to mark power relations. In this process, children are exposed to culturally specific routines that forge pragmatic competencies on par with universal linguistic and cognitive traits (e.g. in acquiring requests, discourse markers, arguments in conflicts). On socialization practices, I would have preferred some discussion of current research on young children’s conversational skills as these become manifest in turn-taking (see Cassillas & Frank 2012, Casillas 2014a,b) and on early social traits in infants as these become manifest in faithful imitation (Hilbrink et al. 2013). This would have been very relevant given Amy Kyratzis’s (2007) work on peer group interactions. Returning to the issue of ToM abilities in Ch. 5, Z contrasts evidence from four-year-olds’ success in false-belief tests, earlier success in linguistic tasks, and eye-gaze infant studies. Children are capable of inferential communication required to process metaphors, resolve ambiguity, and understand hints at the age of two and a half years and long before they pass explicit versions of the false-belief task...

Self-mockery: A study of Persian multi-party interactions

AbstractThis study investigated self-mockery as an exemplar of jocular mockery. Drawing on authentic verbal data, collected in a university dormitory in Isfahan, Iran, this paper examined the interactional functions of self-mockery, and how self-mockery arose and was responded to in Persian face-to-face multi-party interactions. Seven cases of self-mockery were identified in the recorded transcripts of six multi-party conversations. Analysis of the transcripts indicates that self-mockery was performed to fulfill three interactional functions: (i) saving one’s own face; (ii) saving the face of the listeners; and (iii) bringing reciprocated amusement to the conversation. Furthermore, self-mockery was performed in response to either humor initiated by other interlocutors, or the display of humiliation. The results also revealed two interactional functions for the recipients’ responses, including (i) saving the face of the self-mocker; and (ii) bringing amusement to the conversation. By and large, the results indicated that the relative appropriateness of the response strategy may depend on the interactional function of self-mockery that the recipient wishes to fulfill. And finally, the results showed that the self-mockers and the recipients go along with each other’s interactional exchanges to maintain interactional solidarity.

Killing Two Birds with One Deceit

This paper explores the workings of deception performed in multi-party interactions, a topic hitherto hardly ever examined by deception philosophers. Deception is here discussed in the light of a neo-Goffmanian classification of (un)ratified hearers and a neo-Gricean version of speaker meaning, anchored in non-reflexive intentionality and accountability, which is shown to operate beyond the speaker-hearer dyad. An utterance, it is argued, may carry different meanings, judged according to their (lack of) intentionality and (non)deceptiveness, towards the individuals performing different hearer roles. The complex mechanisms of deception with regard to different hearers are illustrated with examples culled from the American television series “House.” Deception in fictional interactions is illustrative of real-life manifestations of deception, yet it brings into focus also those rare ones, which are in the centre of philosophical attention.