https://hdl.handle.net/10481/19604 2026-04-11T20:31:16Z https://hdl.handle.net/10481/104995 A Survey on Multi-User Conversational Interfaces Wagner, Nicolas; Kraus, Matthias; Minker, Wolfgang; Griol Barres, David; Callejas Carrión, Zoraida This paper investigates the evolving landscape of Multi-User Conversational Interfaces, addressing the limitations of traditional systems that primarily focus on single-user interactions. As real-world applications grow more complex, there is a pressing need for conversational systems capable of facilitating dialogues among multiple participants. Our systematic survey reviews recent advancements in the field, highlighting innovative architectures, application domains, user and dialogue modelling, and evaluation metrics tailored for multi-user contexts. We conduct a comprehensive analysis of relevant literature, employing both quantitative and qualitative methodologies to identify common patterns and challenges in multi-user interactions. The findings underscore the importance of developing robust interfaces that can effectively manage overlapping dialogues, ensure collaborative group work, and enhance overall conversational quality. This work contributes to the understanding of Multi-User Conversational Interfaces and may help as a basis for future research aiming to develop more natural, user-friendly, and effective conversational interfaces. The research leading to these results has received funding from the Spanish R&D&i project TrustBoost (PID2023-150584OB-C21 and PID2023-150584OB-C22) financed by ICIU/AEI/10.13039/-501100011033 and from FEDER, EU. It has also received funding the HORIZON EUROPE MSCA-Staff Exchanges Action entitled “CRYSTAL, Conversational Systems for Emotional Support and Customer Assistance” (Grant no. 101182965). Additionally, it has also received funding from the project FORSocialRobots, financed by the Bavarian Research Foundation (AZ1594-23). https://hdl.handle.net/10481/94974 Combining Generative AI and PPTalk Service Specification for Dynamic and Adaptive Task-Oriented Chatbots Rodríguez-Sánchez, María Jesús; Callejas Carrión, Zoraida; Ruiz-Zafra, Ángel; Benghazi Akhlaki, Kawtar In recent years, chatbots have become increasingly prevalent in various business domains, providing services such as booking flights, making hotel reservations, and scheduling appointments. These systems, known as task-oriented chatbots, initiate a conversation to collect the necessary data and subsequently invoke a specific web service to complete the task. Traditionally, they operate on the basis of predefined rules or are trained with specific task data. While effective, this approach is often rigid and lacks adaptability to the evolving peculiarities of individual businesses. For instance, a chatbot designed for general restaurant reservations will request common data such as the number of diners or reservation time, but may fail to accommodate specific preferences such as terrace seating, buffet options, or karaoke availability. To address the limitations of traditional task-oriented chatbots, we propose an innovative approach leveraging generative AI and a novel service specification concept called PPTalk. This approach enables chatbots to dynamically introduce business-specific elements into conversations, enhancing their adaptability to the unique characteristics of each business. We have developed a proof of concept to demonstrate the feasibility and effectiveness of our proposal, obtaining highly positive results. https://hdl.handle.net/10481/88570 A data-driven approach to spoken dialog segmentation Griol Barres, David; Molina, José Manuel; Sanchis, Araceli; Callejas Carrión, Zoraida With the advances in Language Technologies and Natural Language Processing, conversational interfaces have begun to play an increasingly important role in the design of human-machine interaction systems in a number of devices and intelligent environments. In this paper, we present a statistical model for spoken dialog segmentation and labeling based on a generative model learned using decision trees. We have applied our proposal in a practical conversational system that helps solving simple and routine software and hardware repairing problems. The results of the evaluation show that automatic segmentation of spoken dialogs is very effective for human-machine dialogs. The same statistical model has been applied to human-human conversations and provides a good baseline as well insights in the model limitation. https://hdl.handle.net/10481/88569 Combining speech- based and linguistic classifiers to recognize emotion in user spoken utterances Griol Barres, David; Molina, José Manuel; Callejas Carrión, Zoraida In this paper we propose to combine speech-based and linguistic classification in order to obtain better emotion recognition results for user spoken utterances. Usually these approaches are considered in isolation and even developed by different communities working on emotion recognition and sentiment analysis. We propose modeling the users emotional state by means of the fusion of the outputs generated with both approaches, taking into account information that is usually neglected in the individual approaches such as the interaction context and errors, and the peculiarities of transcribed spoken utterances. The fusion approach allows to employ different recognizers and can be integrated as an additional module in the architecture of a spoken conversational agent, using the information generated as an additional input for the dialog manager to decide the next system response. We have evaluated our proposal using three emotionally-colored databases and obtained very positive results. https://hdl.handle.net/10481/88567 Developing enhanced conversational agents for social virtual worlds Griol Barres, David; Sanchis, Araceli; Molina, José Manuel; Callejas Carrión, Zoraida In this paper, we present a methodology for the development of embodied conversational agents for social virtual worlds. The agents provide multimodal communication with their users in which speech interaction is included. Our proposal combines different techniques related to Artificial Intelligence, Natural Language Processing, Affective Computing, and User Modeling. A statistical methodology has been developed to model the system conversational behavior, which is learned from an initial corpus and improved with the knowledge acquired from the successive interactions. In addition, the selection of the next system response is adapted considering information stored into user’s profiles and also the emotional contents detected in the user’s utterances. Our proposal has been evaluated with the successful development of an embodied conversational agent which has been placed in the Second Life social virtual world. The avatar includes the different models and interacts with the users who inhabit the virtual world in order to provide academic information. The experimental results show that the agent’s conversational behavior adapts successfully to the specific characteristics of users interacting in such environments.