# An End-to-End Conversational Style Matching Agent

arXiv: https://arxiv.org/abs/1904.02760 · HTML: https://mlsanity.com/paper/1904.02760/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [Can LLMs Generate Behaviors for Embodied Virtual Agents Based on Personality Traits?](https://mlsanity.com/paper/2508.21087/) (2025)
- [The Importance of Multimodal Emotion Conditioning and Affect Consistency for Embodied Conversational Agents](https://mlsanity.com/paper/2309.15311/) (2023)
- [Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue](https://mlsanity.com/paper/2311.13061/) (2023)
- [LLM-Mediated Domain-Specific Voice Agents: The Case of TextileBot](https://mlsanity.com/paper/2406.10590/) (2024)
- [Towards the "Digital Me": A vision of authentic Conversational Agents powered by personal Human Digital Twins](https://mlsanity.com/paper/2506.23826/) (2025)
- [The Adaptation Paradox: Agency vs. Mimicry in Companion Chatbots](https://mlsanity.com/paper/2509.12525/) (2025)
- [Analysis and Utilization of Entrainment on Acoustic and Emotion Features in User-agent Dialogue](https://mlsanity.com/paper/2212.03398/) (2022)

## Abstract (arXiv)

We present an end-to-end voice-based conversational agent that is able to engage in naturalistic multi-turn dialogue and align with the interlocutor's conversational style. The system uses a series of deep neural network components for speech recognition, dialogue generation, prosodic analysis and speech synthesis to generate language and prosodic expression with qualities that match those of the user. We conducted a user study (N=30) in which participants talked with the agent for 15 to 20 minutes, resulting in over 8 hours of natural interaction data. Users with high consideration conversational styles reported the agent to be more trustworthy when it matched their conversational style. Whereas, users with high involvement conversational styles were indifferent. Finally, we provide design guidelines for multi-turn dialogue interactions using conversational style adaptation.