activity
20242026
collaborators

6 papers

eess.AS2026

The USTC-NERCSLIP Systems for the CHiME-9 MCoRec Challenge

Ya Jiang, Ruoyu Wang, Jingxuan Zhang +19

This report details our submission to the CHiME-9 MCoRec Challenge on recognizing and clustering multiple concurrent natural conversations within indoor social settings. Unlike con…

eess.AS2025

Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarization

Jiangyu Han, Ruoyu Wang, Yoshiki Masuyama +4

Self-supervised models such as WavLM have demonstrated strong performance for neural speaker diarization. However, these models are typically pre-trained on single-channel recordin…

cs.SD2025

Latent Swap Joint Diffusion for 2D Long-Form Latent Generation

Yusheng Dai, Chenxi Wang, Chang Li +7

This paper introduces Swap Forward (SaFa), a modality-agnostic and efficient method to generate seamless and coherence long spectrum and panorama through latent swap joint diffusio…

cs.SD2025

Exploring Speaker Diarization with Mixture of Experts

Gaobin Yang, Maokui He, Shutong Niu +3

In this paper, we propose a novel neural speaker diarization system using memory-aware multi-speaker embedding with sequence-to-sequence architecture (NSD-MS2S), which integrates a…

cs.SD2025

Quality-aware Masked Diffusion Transformer for Enhanced Music Generation

Chang Li, Ruoyu Wang, Lijuan Liu +7

Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation. Achieving high quality and diversity in this pr…

eess.AS2024

DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions

Shu-Tong Niu, Jun Du, Ruo-Yu Wang +4

We propose a single-channel Deep Cascade Fusion of Diarization and Separation (DCF-DS) framework for back-end automatic speech recognition (ASR), combining neural speaker diarizati…