F-Actor：全双工模型中的可控对话行为
F-Actor: Controllable Conversational Behaviour in Full-Duplex Models
AI总结：
本文提出首个可训练的全双工对话语音模型，通过冻结音频编码器仅微调语言模型，在有限资源下实现高效训练，支持通过指令控制说话声音、话题和对话行为。
摘要：
本文提出首个可训练的全双工对话语音模型，通过冻结音频编码器仅微调语言模型，在有限资源下实现高效训练，支持通过指令控制说话声音、话题和对话行为。
英文摘要：
Spoken conversational systems require more than accurate speech generation to have human-like conversations: to feel natural and engaging, they must produce conversational behaviour that adapts dynamically to the context. Current spoken conversational systems, however, rarely allow such customization, limiting their naturalness and usability. In this work, we present the first open, instruction-following full-duplex conversational speech model that can be trained efficiently under typical academic resource constraints. By keeping the audio encoder frozen and finetuning only the language model, our model requires just 2,000 hours of data, without relying on large-scale pretraining or multi-stage optimization. The model can follow explicit instructions to control speaker voice, conversation topic, conversational behaviour (e.g., backchanneling and interruptions), and dialogue initiation. We propose a single-stage training protocol and systematically analyze design choices. Both the model and training code is released to enable reproducible research on controllable full-duplex speech systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
