Scholar

Zhengyan Sheng

Google Scholar ID: tzU_I7YAAAAJ

University of Science and Technology of China

Speech SynthesisMultimodality-driven Speaker Generation

Google Scholar↗

Citations & Impact

All-time

Citations

214

H-index

6

i10-index

3

Publications

15

Co-authors

0

Contact

No contact links provided.

Publications

6 items

JoyVoice: Long-Context Conditioning for Anthropomorphic Multi-Speaker Conversational Synthesis

2025

Cited

0

The First Voice Timbre Attribute Detection Challenge

2025

Cited

0

Introducing voice timbre attribute detection

2025

Cited

1

SyncSpeech: Low-Latency and Efficient Dual-Stream Text-to-Speech based on Temporal Masked Transformer

2025

Cited

0

Unispeaker: A Unified Approach for Multimodality-driven Speaker Generation

2025

Cited

0

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

2024

Cited

1

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)