24 citations · 36 across the 2 of their papers we have counts for
5 papers
High-Fidelity Song Generation with Joint Discrete and Continuous Modeling
Zheqi Dai, Zhiyue Wu, Ruibin Yuan +5
Generating a full song from lyrics and a style description requires long-range musical planning without sacrificing vocal and instrumental detail. Low-rate discrete semantic tokens…
HMU-Bench: Hierarchical Music Understanding Benchmark for Omni Models
Zheqi Dai, Boyang Wang, Zhiyue Wu +6
Music-understanding benchmarks should identify both the evidence available to a model and the operations a correct answer requires. We introduce HMU-Bench, a bilingual benchmark wi…
StepAudio 3 Music Technical Report
Chengli Feng, Zhiyue Wu, Jiahao Song +10
We introduce StepAudio 3 Music, a large-scale, long-form music generation model that supports explicit musical planning and open-domain text-controlled generation. The StepAudio Mu…
BART based semantic correction for Mandarin automatic speech recognition system
Yun Zhao, Xuerui Yang, Jinchao Wang +3
Although automatic speech recognition (ASR) systems achieved significantly improvements in recent years, spoken language recognition error occurs which can be easily spotted by hum…
A novel pyramidal-FSMN architecture with lattice-free MMI for speech recognition
Xuerui Yang, Jiwei Li, Xi Zhou
Deep Feedforward Sequential Memory Network (DFSMN) has shown superior performance on speech recognition tasks. Based on this work, we propose a novel network architecture which int…