Follow
Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models https://arxiv.org/abs/2603.25750 #eess.AS #cs.SD #cs.AI
Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models https://arxiv.org/abs/2603.25750 #eess.AS #cs.SD #cs.AI