9 papers
Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation
Zhen Ye, Xu Tan, Yiming Li +10
Spoken dialogue models typically start from text LLM backbones, yet reasoning often degrades when conditioning on speech instead of text. We attribute part of this modality gap to…
ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction
LeKai Yu, Hao Liu, Kun Wang +4
In this report, we present our third-place solution for the DataMFM Challenge Track 1: Document Parsing. This track requires models to recover structured Markdown documents from do…
UniVoice: A Unified Model for Speech and Singing Voice Generation
Junjie Zheng, Huixin Xue, Shihong Ren +3
Text-to-speech (TTS) and singing voice synthesis (SVS) both aim to generate human vocal audio from symbolic inputs, but they impose different requirements on the generation process…
EmoOmni: Bridging Emotional Understanding and Expression in Omni-Modal LLMs
Wenjie Tian, Zhixian Zhao, Jingbin Hu +4
The evolution of Omni-Modal Large Language Models~(Omni-LLMs) has revolutionized human--computer interaction, enabling unified audio-visual perception and speech response. However,…
YuE: Scaling Open Foundation Models for Long-Form Music Generation
Ruibin Yuan, Hanfeng Lin, Shuyue Guo +55
We tackle the task of long-form music generation--particularly the challenging \textbf{lyrics-to-song} problem--by introducing YuE, a family of open foundation models based on the…
Inference-time Scaling for Diffusion-based Audio Super-resolution
Yizhu Jin, Zhen Ye, Zeyue Tian +4
Diffusion models have demonstrated remarkable success in generative tasks, including audio super-resolution (SR). In many applications like movie post-production and album masterin…