Awesome Speech Audio
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Zexu Pan — most-cited papers & profile · Speech Audio
← authors
·
overview
Zexu Pan
15
papers ·
29
citations ·
14
h-index
Alibaba Group (Cayman Islands) · Alibaba Group (United States) · Alibaba Group (China) · University of Science and Technology Beijing
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
2024 · 20 citations
Selective Listening by Synchronizing Speech with Lips
2021 · 4 citations
Muse: Multi-modal target speaker extraction with visual cues
2020 · 2 citations
Conditional Latent Diffusion-Based Speech Enhancement Via Dual Context Learning
2025 · 1 citations
USEV: Universal Speaker Extraction with Visual Cue
2021 · 1 citations
Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction
2023 · 1 citations
Online Audio-Visual Autoregressive Speaker Extraction
2025
Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation
2025
A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction
2022
VCSE: Time-Domain Visual-Contextual Speaker Extraction Network
2022
Target Active Speaker Detection with Audio-visual Cues
2023
Audio-Visual Active Speaker Extraction for Sparsely Overlapped Multi-talker Speech
2023
LocSelect: Target Speaker Localization with an Auditory Selective Hearing Mechanism
2023
Enhanced Reverberation as Supervision for Unsupervised Speech Separation
2024
Top co-authors
Haizhou Li
· 8
Ruijie Tao
· 4
Gordon Wichern
· 3
Jonathan Le Roux
· 3
Meng Ge
· 3
Bin Ma
· 2
Chenglin Xu
· 2
Fran\c{c}ois G. Germain
· 2
Kohei Saijo
· 2
Kun Zhou
· 2
Shengkui Zhao
· 2
Wupeng Wang
· 2
Topics
Speech Enhancement
Audio Understanding
Multimodal Audio
Speaker Analysis
Speech Recognition
Speech Translation
Text-to-Speech