AIBullisharXiv โ CS AI ยท 3d ago6/10
๐ง
DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization
DuplexCascade introduces a VAD-free cascaded streaming pipeline that enables full-duplex speech-to-speech dialogue while maintaining LLM intelligence. The system converts traditional long utterance turns into micro-turn interactions using special control tokens to coordinate turn-taking and response timing.