This study analyses how state-of-the-art multimodal large language models (MLLMs) can predict the next speaker in multi-party conversations. Through experimental and qualitative analyses, we found that MLLMs are able to infer a plausible next speaker based solely on linguistic context and their internalized knowledge. However, even in cases where the next speaker is not uniquely determined, MLLMs exhibit a bias toward overpredicting a single participant as the next speaker. We further showed that this bias can be mitigated by explicitly providing knowledge of turn-taking rules. In addition, we observed that visual input can sometimes contribute to more accurate predictions, while in other cases it leads to erroneous judgments. Overall, however, no clear effect of visual input was observed.

We present a multilingual, continuous backchannel prediction model for Japanese, English, and Chinese, and use it to investigate cross-linguistic timing behavior. The model is Transformer-based and operates at the frame level, jointly trained with auxiliary tasks on approximately 300 hours of dyadic conversations. Across all three languages, the multilingual model matches or surpasses monolingual baselines, indicating that it learns both language-universal cues and language-specific timing patterns. Zero-shot transfer with two-language training remains limited, underscoring substantive cross-lingual differences. Perturbation analyses reveal distinct cue usage: Japanese relies more on short-term linguistic information, whereas English and Chinese are more sensitive to silence duration and prosodic variation; multilingual training encourages shared yet adaptable representations and reduces overreliance on pitch in Chinese. A context-length study further shows that Japanese is relatively robust to shorter contexts, while Chinese benefits markedly from longer contexts. Finally, we integrate the trained model into a real-time processing software, demonstrating CPU-only inference. Together, these findings provide a unified model and empirical evidence for how backchannel timing differs across languages, informing the design of more natural, culturally-aware spoken dialogue systems.

While most existing dialogue studies focus on dyadic (one-on-one) interactions, research on multi-party dialogues has gained increasing importance. One key challenge in multi-party dialogues is identifying and interpreting the relationships between participants. This study focuses on multi-party chat corpus and aims to estimate participant pairs with specific relationships, such as family and acquaintances. We evaluated the performance of large language models (LLMs) in estimating these relationships, comparing them with a logistic regression model that uses interpretable textual features, including the number of turns and the frequency of honorific expressions. The results show that even advanced LLMs struggle with social relationship estimation, performing worse than a simple heuristic-based approach. This finding highlights the need for further improvement in enabling LLMs to naturally capture social relationships in multi-party dialogues.

Understanding hand gestures is essential for human communication, yet it remains unclear how well multimodal large language models (MLLMs) comprehend them. In this paper, we examine MLLMs’ ability to interpret indexical gestures, which require external referential grounding, in comparison to iconic gestures, which depict imagery, and symbolic gestures, which are conventionally defined. We hypothesize that MLLMs, lacking real-world referential understanding, will struggle significantly with indexical gestures. To test this, we manually annotated five gesture type labels to 925 gesture instances from the Miraikan SC Corpus and analyzed gesture descriptions generated by state-of-the-art MLLMs, including GPT-4o. Our findings reveal a consistent weakness across models in interpreting indexical gestures, suggesting that MLLMs rely heavily on linguistic priors or commonsense knowledge rather than grounding their interpretations in visual or contextual cues.

This paper introduces the human-like embodied AI interviewer which integrates android robots equipped with advanced conversational capabilities, including attentive listening, conversational repairs, and user fluency adaptation. Moreover, it can analyze and present results post-interview. We conducted a real-world case study at SIGDIAL 2024 with 42 participants, of whom 69% reported positive experiences. This study demonstrated the system’s effectiveness in conducting interviews just like a human and marked the first employment of such a system at an international conference. The demonstration video is available at https://youtu.be/jCuw9g99KuE.

Implementation of spoken dialogue systems can be time-consuming, in particular for people who are not familiar with managing dialogue states and turn-taking in real-time. A GUI-based system where the user can quickly understand the dialogue flow allows rapid prototyping of experimental and real-world systems. In this demonstration we present ScriptBoard, a tool for creating dialogue scenarios which is independent of any specific robot platform. ScriptBoard has been designed with multi-party scenarios in mind and makes use of large language models to both generate dialogue and make decisions about the dialogue flow. This program promotes both flexibility and reproducibility in spoken dialogue research and provides everyone the opportunity to design and test their own dialogue scenarios.

Laughter serves as a multifaceted communicative signal in human interaction, yet its identification within dialogue presents a significant challenge for conversational AI systems. This study addresses this challenge by annotating laughable contexts in Japanese spontaneous text conversation data and developing a taxonomy to classify the underlying reasons for such contexts. Initially, multiple annotators manually labeled laughable contexts using a binary decision (laughable or non-laughable). Subsequently, an LLM was used to generate explanations for the binary annotations of laughable contexts, which were then categorized into a taxonomy comprising ten categories, including “Empathy and Affinity” and “Humor and Surprise,” highlighting the diverse range of laughter-inducing scenarios. The study also evaluated GPT-4o’s performance in recognizing the majority labels of laughable contexts, achieving an F1 score of 43.14%. These findings contribute to the advancement of conversational AI by establishing a foundation for more nuanced recognition and generation of laughter, ultimately fostering more natural and engaging human-AI interactions.

Handling multi-party dialogues represents a significant step for advancing spoken dialogue systems, necessitating the development of tasks specific to multi-party interactions. To address this challenge, we are constructing a multi-modal multi-party dialogue corpus of triadic (three-participant) discussions. This paper focuses on the task of addressee recognition, identifying who is being addressed to take the next turn, a critical component unique to multi-party dialogue systems. A subset of the corpus was annotated with addressee information, revealing that explicit addressees are indicated in approximately 20% of conversational turns. To evaluate the task’s complexity, we benchmarked the performance of a large language model (GPT-4o) on addressee recognition. The results showed that GPT-4o achieved an accuracy only marginally above chance, underscoring the challenges of addressee recognition in multi-party dialogue. These findings highlight the need for further research to enhance the capabilities of large language models in understanding and navigating the intricacies of multi-party conversational dynamics.

In human conversations, short backchannel utterances such as “yeah” and “oh” play a crucial role in facilitating smooth and engaging dialogue.These backchannels signal attentiveness and understanding without interrupting the speaker, making their accurate prediction essential for creating more natural conversational agents.This paper proposes a novel method for real-time, continuous backchannel prediction using a fine-tuned Voice Activity Projection (VAP) model.While existing approaches have relied on turn-based or artificially balanced datasets, our approach predicts both the timing and type of backchannels in a continuous and frame-wise manner on unbalanced, real-world datasets.We first pre-train the VAP model on a general dialogue corpus to capture conversational dynamics and then fine-tune it on a specialized dataset focused on backchannel behavior.Experimental results demonstrate that our model outperforms baseline methods in both timing and type prediction tasks, achieving robust performance in real-time environments.This research offers a promising step toward more responsive and human-like dialogue systems, with implications for interactive spoken dialogue applications such as virtual assistants and robots.

Turn-taking prediction models are essential components in spoken dialogue systems and conversational robots. Recent approaches leverage transformer-based architectures to predict speech activity continuously and in real-time. In this study, we propose a novel model that enables turn-taking prediction to be dynamically controlled via textual prompts. This approach allows intuitive and explicit control through instructions such as “faster” or “calmer,” adapting dynamically to conversational partners and contexts. The proposed model builds upon a transformer-based voice activity projection (VAP) model, incorporating textual prompt embeddings into both channel-wise transformers and a cross-channel transformer. We evaluated the feasibility of our approach using over 950 hours of human-human spoken dialogue data. Since textual prompt data for the proposed approach was not available in existing datasets, we utilized a large language model (LLM) to generate synthetic prompt sentences. Experimental results demonstrated that the proposed model improved prediction accuracy and effectively varied turn-taking timing behaviors according to the textual prompts.

This paper investigates the application of voice activity projection (VAP), a predictive turn-taking model for spoken dialogue, on multilingual data, encompassing English, Mandarin, and Japanese. The VAP model continuously predicts the upcoming voice activities of participants in dyadic dialogue, leveraging a cross-attention Transformer to capture the dynamic interplay between participants. The results show that a monolingual VAP model trained on one language does not make good predictions when applied to other languages. However, a multilingual model, trained on all three languages, demonstrates predictive performance on par with monolingual models across all languages. Further analyses show that the multilingual model has learned to discern the language of the input signal. We also analyze the sensitivity to pitch, a prosodic cue that is thought to be important for turn-taking. Finally, we compare two different audio encoders, contrastive predictive coding (CPC) pre-trained on English, with a recent model based on multilingual wav2vec 2.0 (MMS).

Recent approaches to empathetic response generation try to incorporate commonsense knowledge or reasoning about the causes of emotions to better understand the user’s experiences and feelings. However, these approaches mainly focus on understanding the causalities of context from the user’s perspective, ignoring the system’s perspective. In this paper, we propose a commonsense-based causality explanation approach for diverse empathetic response generation that considers both the user’s perspective (user’s desires and reactions) and the system’s perspective (system’s intentions and reactions). We enhance ChatGPT’s ability to reason for the system’s perspective by integrating in-context learning with commonsense knowledge. Then, we integrate the commonsense-based causality explanation with both ChatGPT and a T5-based model. Experimental evaluations demonstrate that our method outperforms other comparable methods on both automatic and human evaluations.

Large language models (LLMs) have brought about a significant transformation in spoken dialogue systems (SDSs). It is anticipated that these systems will be implemented into diverse robotic applications and employed in a variety of social settings. The author presents research interest with the aim of realizing social SDSs from multiple perspectives, including task design, turn-taking mechanisms, and evaluation methodologies. Additionally, future research in social SDSs should delve into a deeper understanding of user mental states and a relationship with society via multi-party conversations. Finally, the author suggests topics for discussion regarding the future directions of SDS researchers in the LLM era.

In recent years, spoken dialogue systems have been applied to job interviews where an applicant talks to a system that asks pre-defined questions, called on-demand and self-paced job interviews. We propose a simultaneous job interview system, where one interviewer can conduct one-on-one interviews with multiple applicants simultaneously by cooperating with the multiple autonomous job interview dialogue systems. However, it is challenging for interviewers to monitor and understand all the parallel interviews done by the autonomous system at the same time. As a solution to this issue, we implemented two automatic dialogue understanding functions: (1) response evaluation of each applicant’s responses and (2) keyword extraction as a summary of the responses. It is expected that interviewers, as needed, can intervene in one dialogue and smoothly ask a proper question that elaborates the interview. We report a pilot experiment where an interviewer conducted simultaneous job interviews with three candidates.

We demonstrate the moderating abilities of a multi-party attentive listening robot system when multiple people are speaking in turns. Our conventional one-on-one attentive listening system generates listener responses such as backchannels, repeats, elaborating questions, and assessments. In this paper, additional robot responses that stimulate a listening user (side participant) to become more involved in the dialogue are proposed. The additional responses elicit assessments and questions from the side participant, making the dialogue more empathetic and lively.

We describe an attentive listening system for the autonomous android robot ERICA. The proposed system generates several types of listener responses: backchannels, repeats, elaborating questions, assessments, generic sentimental responses, and generic responses. In this paper, we report a subjective experiment with 20 elderly people. First, we evaluated each system utterance excluding backchannels and generic responses, in an offline manner. It was found that most of the system utterances were linguistically appropriate, and they elicited positive reactions from the subjects. Furthermore, 58.2% of the responses were acknowledged as being appropriate listener responses. We also compared the proposed system with a WOZ system where a human operator was operating the robot. From the subjective evaluation, the proposed system achieved comparable scores in basic skills of attentive listening such as encouragement to talk, focused on the talk, and actively listening. It was also found that there is still a gap between the system and the WOZ for more sophisticated skills such as dialogue understanding, showing interest, and empathy towards the user.

Attentive listening systems are designed to let people, especially senior people, keep talking to maintain communication ability and mental health. This paper addresses key components of an attentive listening system which encourages users to talk smoothly. First, we introduce continuous prediction of end-of-utterances and generation of backchannels, rather than generating backchannels after end-point detection of utterances. This improves subjective evaluations of backchannels. Second, we propose an effective statement response mechanism which detects focus words and responds in the form of a question or partial repeat. This can be applied to any statement. Moreover, a flexible turn-taking mechanism is designed which uses backchannels or fillers when the turn-switch is ambiguous. These techniques are integrated into a humanoid robot to conduct attentive listening. We test the feasibility of the system in a pilot experiment and show that it can produce coherent dialogues during conversation.