paper-with-me

Papers

Beyond Turn-taking: Introducing Text-based Overlap into Human-LLM Interactions

2025-01-30 · Jiwoo Kim, Minsuk Chang, JinYeong Bak

Traditional text-based human-AI interactions often adhere to a strict turn-taking approach. In this research, we propose a novel approach that incorporates overlapping messages, mirroring natural human conversations. Through a formative study, we observed that even in text-based contexts, users instinctively engage in overlapping behaviors like "A: Today I went to-" "B: yeah." To capitalize on these insights, we developed OverlapBot, a prototype chatbot where both AI and users can initiate overlapping. Our user study revealed that OverlapBot was perceived as more communicative and immersive than traditional turn-taking chatbot, fostering faster and more natural interactions. Our findings contribute to the understanding of design space for overlapping interactions. We also provide recommendations for implementing overlap-capable AI interactions to enhance the fluidity and engagement of text-based conversations.

📄 PDF Abstract BibTeX arXiv:2501.18103

Code (0)

등록된 구현이 없습니다.

Tasks

Chatbot

Similar Papers 제목 키워드 기반

Pardon the Interruption: Managing Turn-Taking through Overlap Resolution in Embodied Artificial Agents

2018-07-01 · WS 2018 7 · Felix Gervits, Matthias Scheutz

Speech overlap is a common phenomenon in natural conversation and in task-oriented interactions. As human-robot interaction (HRI) becomes more sophisticated, the need to effectively manage turn-taking and resolve overlap…

Spoken Dialogue Systems

Automated mapping of competitive and collaborative overlapping talk in video meetings.

2022-04-28 · CHI EA '22: CHI Conference on Human Factors in Computing Systems Extended Abstracts 2022 4 · Eleni Margariti, Sean Rintel, Brendan Murphy, Abigail Sellen

Video meetings are notorious for difficulties with conversational turn-taking, which has impacts on inclusion and outcomes. We present a scalable automatic process to categorize turn-taking patterns in remote meetings ba…

Speech Interruption Detection

Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR

2026-04-03 · Zhennan Lin, Shuai Wang, Zhaokai Sun, Pengyuan Xie 외 arxiv

Transcribing and understanding multi-speaker conversations requires speech recognition, speaker attribution, and timestamp localization. While speech LLMs excel at single-speaker tasks, multi-speaker scenarios remain cha…

Speech Recognition

Investigating Speech Features for Continuous Turn-Taking Prediction Using LSTMs

2018-06-29 · Matthew Roddy, Gabriel Skantze, Naomi Harte

For spoken dialog systems to conduct fluid conversational interactions with users, the systems must be sensitive to turn-taking cues produced by a user. Models should be designed so that effective decisions can be made a…

Fast When, Careful Who: Dual-Process Multiparty Turn-Taking with Diffusion Augmentation

2026-06-15 · Rutherford A. Patamia, Ming Liu, Wei Luo, Favour Ekong 외 arxiv

Reliable turn-taking is essential for spoken dialogue systems. However, most existing methods are designed for two-speaker interaction and struggle with realistic multiparty audio containing overlap and rapid speaker cha…

Data Augmentation