activity
20202026
most citedUnified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition

46 citations · 78 across the 18 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models

Han Zhu, Lingxuan Ye, Wei Kang +7

We present OmniVoice, a massively multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discret…