activity
20232025
most citedOne-Class Knowledge Distillation for Spoofing Speech Detection

2 citations · 4 across the 5 of their papers we have counts for

collaborators

8 papers

cs.SD2025

Controlling your Attributes in Voice

Xuyuan Li, Zengqiang Shang. Li Wang, Pengyuan Zhang

Attribute control in generative tasks aims to modify personal attributes, such as age and gender while preserving the identity information in the source sample. Although significan…

cs.SD2025

Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation

Haorui He, Zengqiang Shang, Chaoren Wang +11

Recent advancements in speech generation have been driven by large-scale training datasets. However, current models struggle to capture the spontaneity and variability inherent in…

cs.SD2024

SF-Speech: Straightened Flow for Zero-Shot Voice Clone

Xuyuan Li, Zengqiang Shang, Hua Hua +4

Recently, neural ordinary differential equations (ODE) models trained with flow matching have achieved impressive performance on the zero-shot voice clone task. Nevertheless, postu…

eess.AS20242 cited

Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation

Haorui He, Zengqiang Shang, Chaoren Wang +11

Recent advancements in speech generation models have been significantly driven by the use of large-scale training data. However, producing highly spontaneous, human-like speech rem…

eess.AS2023

Enhancing Spoofing Speech Detection Using Rhythm Information

Jingze Lu, Yuxiang Zhang, Wenchao Wang +2

Current spoofing speech detection systems need more convincing evidence. In this paper, the flaws of rhythm information inherent in the TTS-generated speech are analyzed to increas…

eess.AS2023

Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features

Yuxiang Zhang, Zhuo Li, Jingze Lu +2

Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods…