Liqun Deng
10 papers · 2021–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (4) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (21)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Keyword Champion
(2)
β‘
Prolific Year
(5)
Conferences
INTERSPEECH (6)
ACL (1)
ICML (1)
IJCAI (1)
NIPS (1)
Top co-authors
Keywords
representation disentanglement
(2)
speech disentanglement
(2)
speech representation
(2)
vector quantization
(2)
voice conversion
(2)
prosody modeling
(2)
mutual information minimization
(1)
attention mechanism
(1)
zero-shot learning
(1)
mutual information
(1)
speech analysis
(1)
pre-trained model
(1)
self-supervised learning
(1)
automatic speech recognition
(1)
singing voice synthesis
(1)
cross-attention mechanism
(1)
music corpus
(1)
streaming model
(1)
acoustic feature
(1)
unsupervised domain adaptation
(1)
Papers
The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
ACL 2026
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
ICML 2025
SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech
INTERSPEECH 2024
reducing multilingual context confusion for end-to-end code-switching automatic speech recognition
INTERSPEECH 2022
CoCA-MDD: A Coupled Cross-Attention based Framework for Streaming Mispronunciation Detection and Diagnosis
INTERSPEECH 2022
Streamable Speech Representation Disentanglement and Multi-Level Prosody Modeling for Live One-Shot Voice Conversion
INTERSPEECH 2022
EditSinger: Zero-Shot Text-Based Singing Voice Editing System with Diverse Prosody Modeling
IJCAI 2022
M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus
NIPS 2022
Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization
INTERSPEECH 2021
VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-Shot Voice Conversion
INTERSPEECH 2021