FSD：一个用于虚假歌曲检测的初始中文数据集
FSD: An Initial Chinese Dataset for Fake Song Detection
AI总结：
本文构建了首个中文虚假歌曲检测（FSD）数据集，并证明使用该数据集训练的ADD模型在歌曲深度伪造检测任务上，平均等错误率比语音训练模型降低了38.58%。
摘要：
歌声合成与歌声转换技术取得了显著进展，彻底改变了音乐体验。然而，这些技术生成的“Deepfake Songs”日益增多，引发了真实性问题。与音频深度伪造检测（ADD）不同，歌曲深度伪造检测领域缺乏专门的数据集或歌曲真实性验证方法。本文初步构建了一个中文虚假歌曲检测（FSD）数据集，以研究歌曲深度伪造检测领域。FSD数据集中的虚假歌曲由五种最先进的歌声合成和歌声转换方法生成。我们在FSD上的初步实验表明，现有的基于语音训练的ADD模型对于歌曲深度伪造检测任务无效。因此，我们采用FSD数据集来训练ADD模型。随后，我们在两种场景下评估这些模型：一种使用原始歌曲，另一种使用分离的音轨。实验结果表明，在FSD测试集上，基于歌曲训练的ADD模型与基于语音训练的ADD模型相比，平均等错误率降低了38.58%。
英文摘要：
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 Detection (ADD), the field of song deepfake detection lacks specialized datasets or methods for song authenticity verification. In this paper, we initially construct a Chinese Fake Song Detection (FSD) dataset to investigate the field of song deepfake detection. The fake songs in the FSD dataset are generated by five state-of-the-art singing voice synthesis and singing voice conversion methods. Our initial experiments on FSD revealed the ineffectiveness of existing speech-trained ADD models for the task of song deepFake detection. Thus, we employ the FSD dataset for the training of ADD models. We subsequently evaluate these models under two scenarios: one with the original songs and another with separated vocal tracks. Experiment results show that song-trained ADD models exhibit a 38.58% reduction in average equal error rate compared to speech-trained ADD models on the FSD test set.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
