Zexu Pan
11 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (22) π Interdisciplinary Bridge π Conference Polyglot (3)
π
Academic Marathon
(5)
π
Cross-Pollinator
(5)
π
Renaissance Researcher
(6)
π
Century Club
(11)
ποΈ
Keyword Collector
(59)
Conferences
INTERSPEECH (9)
AAAI (1)
IJCAI (1)
Top co-authors
Keywords
speaker extraction
(4)
visual cue
(2)
cocktail party problem
(2)
attention mechanism
(2)
target speaker extraction
(2)
multimodal learning
(2)
image synthesis
(1)
speaker embedding
(1)
audio-visual learning
(1)
audio signal processing
(1)
video processing
(1)
signal processing
(1)
audio source separation
(1)
occlusion detection
(1)
speech enhancement
(1)
loss function
(1)
deep neural network
(1)
neural network optimization
(1)
autoregressive model
(1)
multi-modal learning
(1)
Papers
M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction
IJCAI 2025
Restoring Speaking Lips from Occlusion for Audio-Visual Speech Recognition
AAAI 2024
PARIS: Pseudo-AutoRegressIve Siamese Training for Online Speech Separation
INTERSPEECH 2024
Enhanced Reverberation as Supervision for Unsupervised Speech Separation
INTERSPEECH 2024
wTIMIT2mix: A Cocktail Party Mixtures Database to Study Target Speaker Extraction for Normal and Whispered Speech
INTERSPEECH 2024
Target Active Speaker Detection with Audio-visual Cues
INTERSPEECH 2023
Speaker Extraction with Detection of Presence and Absence of Target Speakers
INTERSPEECH 2023
Rethinking the Visual Cues in Audio-Visual Speaker Extraction
INTERSPEECH 2023
VCSE: Time-Domain Visual-Contextual Speaker Extraction Network
INTERSPEECH 2022
A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction
INTERSPEECH 2022
Multi-Modal Attention for Speech Emotion Recognition
INTERSPEECH 2020