Výsledky vyhledávání - "Cheng, Haonan"

Report

Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge

Autor: Xie, Yuankun, Wang, Xiaopeng, Wang, Zhiyong, Fu, Ruibo, Wen, Zhengqi, Cheng, Haonan, Ye, Long

ASVspoof5, the fifth edition of the ASVspoof series, is one of the largest global audio security challenges. It aims to advance the development of countermeasure (CM) to discriminate bonafide and spoofed speech utterances. In this paper, we focus on

Externí odkaz: http://arxiv.org/abs/2408.06922

Zobrazit plný text záznamu

Report

EVA-Score: Evaluating Abstractive Long-form Summarization on Informativeness through Extraction and Validation

Autor: Fan, Yuchen, Zhong, Xin, Wan, Yazhe, Wang, Chengsi, Cheng, Haonan, Wu, Gaoche, Ding, Ning, Zhou, Bowen

Since LLMs emerged, more attention has been paid to abstractive long-form summarization, where longer input sequences indicate more information contained. Nevertheless, the automatic evaluation of such summaries remains underexplored. The current eva

Externí odkaz: http://arxiv.org/abs/2407.04969

Zobrazit plný text záznamu

Report

The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio

Autor: Xie, Yuankun, Lu, Yi, Fu, Ruibo, Wen, Zhengqi, Wang, Zhiyong, Tao, Jianhua, Qi, Xin, Wang, Xiaopeng, Liu, Yukun, Cheng, Haonan, Ye, Long, Sun, Yi

With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an urgent need for generalized detection methods. ALM-based deepfake audio currently exhibits widespread, high deception, and type versatility, posing a significant c

Externí odkaz: http://arxiv.org/abs/2405.04880

Zobrazit plný text záznamu

Report

An Efficient Temporary Deepfake Location Approach Based Embeddings for Partially Spoofed Audio Detection

Autor: Xie, Yuankun, Cheng, Haonan, Wang, Yutian, Ye, Long

Partially spoofed audio detection is a challenging task, lying in the need to accurately locate the authenticity of audio at the frame level. To address this issue, we propose a fine-grained partially spoofed audio detection method, namely Temporal D

Externí odkaz: http://arxiv.org/abs/2309.03036

Zobrazit plný text záznamu

Report

FSD: An Initial Chinese Dataset for Fake Song Detection

Autor: Xie, Yuankun, Zhou, Jingjing, Lu, Xiaolin, Jiang, Zhenghao, Yang, Yuxin, Cheng, Haonan, Ye, Long

Singing voice synthesis and singing voice conversion have significantly advanced, revolutionizing musical experiences. However, the rise of "Deepfake Songs" generated by these technologies raises concerns about authenticity. Unlike Audio DeepFake Det

Externí odkaz: http://arxiv.org/abs/2309.02232

Zobrazit plný text záznamu