Author name: Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu, Hung-yi Lee, James Glass

arXiv:2603.22267v2 Announce Type: replace-cross
Abstract: We introduce TiCo, a time-controllable spoken dialogue model (SDM) that follows time-constrained instructions (e.g., “Please generate a response lasting about 15 seconds”) and generates spoken …