8 papers
Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy
Ke Xue, Rongfei Fan, Kai Li +3
Diffusion models have recently set new benchmarks in Speech Enhancement (SE). However, most existing score-based models treat speech spectrograms merely as generic 2D images, apply…
FGNet: Leveraging Feature-Guided Attention to Refine SAM2 for 3D EM Neuron Segmentation
Zhenghua Li, Hang Chen, Zihao Sun +2
Accurate segmentation of neural structures in Electron Microscopy (EM) images is paramount for neuroscience. However, this task is challenged by intricate morphologies, low signal-…
BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective
Andong Li, Tong Lei, Rilin Chen +5
This paper revisits the neural vocoder task through the lens of audio restoration and propose a novel diffusion vocoder called BridgeVoC. Specifically, by rank analysis, we compare…
Advances in Speech Separation: Techniques, Challenges, and Future Trends
Kai Li, Guo Chen, Wendi Sang +8
The field of speech separation, addressing the "cocktail party problem", has seen revolutionary advances with DNNs. Speech separation enhances clarity in complex acoustic environme…
Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder
Runxuan Yang, Kai Li, Guo Chen +1
This paper addresses the challenge of enhancing the realism of vocoder-generated singing voice audio by mitigating the distinguishable disparities between synthetic and real-life r…
Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation
Guo Chen, Kai Li, Runxuan Yang +1
Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information. To address this, we propose the T…