Saved in:
Bibliographic Details
Main Authors: Lu, Yudong, Niu, Yazhe, Hu, Shuai, Wang, Haolin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.01268
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912409136922624
author Lu, Yudong
Niu, Yazhe
Hu, Shuai
Wang, Haolin
author_facet Lu, Yudong
Niu, Yazhe
Hu, Shuai
Wang, Haolin
contents CleanS2S is a framework for human-like speech-to-speech interaction that advances conversational AI through single-file implementation and proactive dialogue capabilities. Our system integrates automatic speech recognition, large language models, and text-to-speech synthesis into a unified pipeline with real-time interruption handling, achieving low transition latency through full-duplex websocket connections and non-blocking I/O. Beyond conventional chatbot paradigms, we pioneer a proactive interaction mechanism, which combines memory systems with Subjective Action Judgement module, enabling five human-like response strategies: interruption, refusal, deflection, silence, and standard response. The memory module dynamically aggregates historical, and contextual data to inform interaction decisions. This approach breaks the rigid turn-based convention by allowing system-initiated dialog control and context-aware response selection. And we propose Action Judgement SFT that assesses input streams for responses strategies. The framework's single-file implementation with atomic configurations offers researchers unprecedented transparency and extensibility for interaction agents. The code of CleanS2S is released at \https://github.com/opendilab/CleanS2S.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01268
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CleanS2S: Single-file Framework for Proactive Speech-to-Speech Interaction
Lu, Yudong
Niu, Yazhe
Hu, Shuai
Wang, Haolin
Artificial Intelligence
Machine Learning
CleanS2S is a framework for human-like speech-to-speech interaction that advances conversational AI through single-file implementation and proactive dialogue capabilities. Our system integrates automatic speech recognition, large language models, and text-to-speech synthesis into a unified pipeline with real-time interruption handling, achieving low transition latency through full-duplex websocket connections and non-blocking I/O. Beyond conventional chatbot paradigms, we pioneer a proactive interaction mechanism, which combines memory systems with Subjective Action Judgement module, enabling five human-like response strategies: interruption, refusal, deflection, silence, and standard response. The memory module dynamically aggregates historical, and contextual data to inform interaction decisions. This approach breaks the rigid turn-based convention by allowing system-initiated dialog control and context-aware response selection. And we propose Action Judgement SFT that assesses input streams for responses strategies. The framework's single-file implementation with atomic configurations offers researchers unprecedented transparency and extensibility for interaction agents. The code of CleanS2S is released at \https://github.com/opendilab/CleanS2S.
title CleanS2S: Single-file Framework for Proactive Speech-to-Speech Interaction
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.01268