2026
Continuous-Token Diffusion for Speaker-Referenced TTS in Multimodal LLMs
ICASSP 2026poster
Unified architectures in multimodal large language models (MLLM) have shown promise in handling diverse tasks within a single framework. In the text-to-speech (TTS) task, current MLLM-based approaches rely on discrete token representations, which disregard the inherently continuous nature of speech…