Scholar
Xinsheng Wang
Google Scholar ID: ZUm3S7EAAAAJ
Hong Kong University of Science and Technology (HKUST)
speech synthesis
singing voice synthesis
voice conversion
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
718
H-index
13
i10-index
19
Publications
20
Co-authors
10
list available
Contact
Email
w.xinshawn@gmail.com
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
15 items
SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation
2026
Cited
0
Joint Learning Global-Local Speaker Classification to Enhance End-to-End Speaker Diarization and Recognition
2026
Cited
0
SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis
2026
Cited
0
The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Era
arXiv.org · 2026
Cited
1
SoulX-Podcast: Towards Realistic Long-form Podcasts with Dialectal and Paralinguistic Diversity
2025
Cited
0
SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization
2025
Cited
0
Evaluating Bias in Spoken Dialogue LLMs for Real-World Decisions and Recommendations
2025
Cited
0
UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice
2025
Cited
0
Load more
Co-authors
5 total
Lei Xie
Northwestern Polytechnical University
jihua zhu
School of Software Engineering, Xi'an Jiaotong University
Odette Scharenborg
Full Professor, Delft University of Technology, The Netherlands
Pengcheng Zhu
Fuxi AI Lab, NetEase Inc.
Mengxiao Bi
Fuxi AI Lab, NetEase Inc.
