Xiaoran Yang

Xiaoran Yang

Auto-generated profile, based on publicly available information

Xiaoran Yang

School of Electronic Information, Wuhan University, Wuhan, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2025 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
XYXiaoran Yang
Xiaoran Yang
HPHanchen Pei
Hanchen Pei
Jacob BenestyJacob Benesty
Jacob Benesty
GHGongping Huang
Gongping Huang
JCJingdong Chen
Jingdong Chen

27 March 2026 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
YWYujin Wang
Yujin Wang
XYXiaoran Yang
Xiaoran Yang
GHGongping Huang
Gongping Huang
Generative models have recently shown strong potential for high-fidelity speech enhancement but suffer from high inference latency due to iterative sampling. In contrast, discriminative models offer fast processing but tend to introduce non-linear distortions that degrade downstream task performance. To bridge this gap, we propose MCFLOW-SE, a spacing-aware generative framework enabling one-step multichannel speech enhancement. By learning an average velocity field that directly maps noisy multichannel observations to clean speech, MCFLOW-SE enables fast one-step inference while effectively leveraging spatial information across channels. Furthermore, sensor spacing is incorporated as positional encoding into the generative process, improving robustness across the evaluated array-spacing configurations. Experiments on both simulated and real-world datasets demonstrate that MCFLOW-SE delivers substantially faster inference than prior generative approaches, while achieving superior Automatic Speech Recognition (ASR) accuracy over discriminative baselines. These results support its potential to bridge the gap between high-fidelity generation and real-time applicability.

1 January 2026 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XYXiaoran Yang
Xiaoran Yang
YDYongyi Deng
Yongyi Deng
YTYanxin Tian
Yanxin Tian
JJJilu Jin
Jilu Jin
XLXueqin Luo
Xueqin Luo
GHGongping Huang
Gongping Huang