Yuancheng Wang
7 papers · 2023–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
π
Conference Polyglot Β· Silver
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(18)
π
Grand Slam
π
Trend Setter
Top co-authors
Research topics
Keywords
zero-shot learning
(2)
direct preference optimization
(2)
self-supervised learning
(2)
preference alignment
(2)
speech synthesis
(1)
dialogue generation
(1)
preference optimization
(1)
multimodal learning
(1)
instruction following
(1)
semantic representation
(1)
vector quantization
(1)
human-computer interaction
(1)
speech intelligibility
(1)
generative model
(1)
benchmark dataset
(1)
reward hacking
(1)
denoising process
(1)
latent diffusion
(1)
latent diffusion model
(1)
semantic token
(1)
Papers
Multi-Metric Preference Alignment for Generative Speech Restoration
AAAI 2026
Advancing Zero-shot Text-to-Speech Intelligibility across Diverse Domains via Preference Alignment
ACL 2025
DualCodec: A Low-Frame-Rate, Semantically-Enhanced Neural Audio Codec for Speech Generation
Interspeech 2025
MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
ICLR 2025
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
ICML 2024
SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
NeurIPS 2024
AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models
NeurIPS 2023