This paper presents a self-supervised method for visual detection of the active speaker in a multi-person spoken interaction scenario. Active speaker detection is a fundamental prerequisite for any artificial cognitive system attempting to acquire language in social settings. The proposed method is intended to complement the acoustic detection of the active speaker, thus improving the system robustness in noisy conditions. The method can detect an arbitrary number of possibly overlapping active speakers based exclusively on visual information about their face. Furthermore, the method does not rely on external annotations, thus complying with cognitive development. Instead, the method uses information from the auditory modality to support learning in the visual domain. This paper reports an extensive evaluation of the proposed method using a large multi-person face-to-face interaction dataset. The results show good performance in a speaker dependent setting. However, in a speaker independent setting the proposed method yields a significantly lower performance. We believe that the proposed method represents an essential component of any artificial cognitive system or robotic platform engaging in social interactions.

This study proposes, develops, and evaluates methods for modeling the eye-gaze direction and head orientation of a person in multiparty open-world dialogues, as a function of low-level communicative signals generated by his/hers interlocutors. These signals include speech activity, eye-gaze direction, and head orientation, all of which can be estimated in real time during the interaction. By utilizing these signals and novel data representations suitable for the task and context, the developed methods can generate plausible candidate gaze targets in real time. The methods are based on Feedforward Neural Networks and Long Short-Term Memory Networks. The proposed methods are developed using several hours of unrestricted interaction data and their performance is compared with a heuristic baseline method. The study offers an extensive evaluation of the proposed methods that investigates the contribution of different predictors to the accurate generation of candidate gaze targets. The results show that the methods can accurately generate candidate gaze targets when the person being modeled is in a listening state. However, when the person being modeled is in a speaking state, the proposed methods yield significantly lower performance.

This paper presents analysis of a previously recorded multimodal interaction dataset. The primary purpose of that dataset is to explore patterns in the focus of visual attention of humans under three different conditions - two humans involved in task-based interaction with a robot; the same two humans involved in task-based interaction where the robot is replaced by a third human, and a free three-party human interaction. The paper presents a data-driven methodology for automatic visual identification of the active speaker based on facial action units (AUs). The paper also presents an evaluation of the proposed methodology on 12 different interactions with an approximate length of 4 hours. The methodology will be implemented on a robot and used to generate natural focus of visual attention behavior during multi-party human-robot interactions

We have developed an interactive virtual audience platform for public speaking training. Users' public speaking behavior is automatically analyzed using multimodal sensors, and ultimodal feedback is produced by virtual characters and generic visual widgets depending on the user's behavior. The flexibility of our system allows to compare different interaction mediums (e.g. virtual reality vs normal interaction), social situations (e.g. one-on-one meetings vs large audiences) and trained behaviors (e.g. general public speaking performance vs specific behaviors).

In this paper, we describe a project that explores a novel experi-mental setup towards building a spoken, multi-modally rich, and human-like multiparty tutoring robot. A human-robotinteraction setup is designed, and a human-human dialogue corpus is collect-ed. The corpus targets the development of a dialogue system platform to study verbal and nonverbaltutoring strategies in mul-tiparty spoken interactions with robots which are capable of spo-ken dialogue. The dialogue task is centered on two participants involved in a dialogueaiming to solve a card-ordering game. Along with the participants sits a tutor (robot) that helps the par-ticipants perform the task, and organizes and balances their inter-action. Differentmultimodal signals captured and auto-synchronized by different audio-visual capture technologies, such as a microphone array, Kinects, and video cameras, were coupled with manual annotations. These are used build a situated model of the interaction based on the participants personalities, their state of attention, their conversational engagement and verbal domi-nance, and how that is correlated with the verbal and visual feed-back, turn-management, and conversation regulatory actions gen-erated by the tutor. Driven by the analysis of the corpus, we will show also the detailed design methodologies for an affective, and multimodally rich dialogue system that allows the robot to meas-ure incrementally the attention states, and the dominance for each participant, allowing the robot head Furhat to maintain a well-coordinated, balanced, and engaging conversation, that attempts to maximize the agreement and the contribution to solve the task. This project sets the first steps to explore the potential of us-ing multimodal dialogue systems to build interactive robots that can serve in educational, team building, and collaborative task solving applications.