38 citations
- Chinese Academy of SciencesCN6 papers
- Peking UniversityCN6 papers
- Tsinghua UniversityCN6 papers
- Microsoft Research Asia (China)CN3 papers
- Peng Cheng LaboratoryCN3 papers
- University of Chinese Academy of SciencesCN3 papers
- Academy of Broadcasting ScienceCN2 papers
- Beihang UniversityCN2 papers
- Beijing Academy of Artificial IntelligenceCN2 papers
- Carnegie Mellon UniversityUS2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- China People's Public Security UniversityCN2 papers
4 papers · 1 filter
Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations
Xue Jiang, Xiulian Peng, Yuan Zhang +1
Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, fol…
Latent-Domain Predictive Neural Speech Coding
Xue Jiang, Xiulian Peng, Huaying Xue +2
Neural audio/speech coding has recently demonstrated its capability to deliver high quality at much lower bitrates than traditional methods. However, existing neural audio/speech c…
A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement
Guochen Yu, Yutian Wang, Hui Wang +2
Cycle-consistent generative adversarial networks (CycleGAN) have shown their promising performance for speech enhancement (SE), while one intractable shortcoming of these CycleGAN-…
Structure-Enhanced Pop Music Generation via Harmony-Aware Learning
Xueyao Zhang, Jinchao Zhang, Yao Qiu +2
Pop music generation has always been an attractive topic for both musicians and scientists for a long time. However, automatically composing pop music with a satisfactory structure…