Author

Sitong Cheng

Observed name: Cheng, Sitong

Institutions: Hong Kong University of Science and Technology, Tencent (China), University of Hong Kong

Observed institutions: Hong Kong University of Science and Technology, Tencent (China), University of Hong Kong, Tsinghua University

OpenAlex ID: A5101078277

ASR-Free Pronunciation Assessment

2020 · Sitong Cheng, Zhixin Liu, et al. · Interspeech (USB) · 31

CN-CELEB: a challenging Chinese speaker recognition dataset

2019 · Fan, Yue, Kang, Jiawen, et al. · arXiv (Cornell University) · 12

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

2025 · Wang, Xinsheng, Jiang, Mingqi, et al. · arXiv (Cornell University) · 1

COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning

2026 · Bian, Weizhen, Cheng, Sitong, et al. · arXiv (Cornell University)

STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity

2026 · Cheng, Sitong, Bian, Weizhen, et al. · arXiv (Cornell University)

ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech

2026 · Xue, Wei, Feng, Junlan, et al. · arXiv (Cornell University)

UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice

2025 · Cheng, Sitong, Bian, Weizhen, et al. · arXiv (Cornell University)

Enhancing Awareness of the Use of Symbols in Chinese Literary Text With the Application of Variation Theory

2010 · Sitong Cheng · INTED proceedings

Works count: 9

Citation count: 44

H-index: 2

I10-index: 2