hashim19/ASVspoofLD

ASVspoof Laundered Database是基于ASVspoof 2019逻辑访问（LA）评估分区的数据库。该数据库通过五种不同类型的加性噪声、三种不同的信噪比（SNR）水平、三种混响噪声、六种不同的重新压缩率、四种不同的重采样因子和一种低通滤波处理，生成了总计1388.22小时的音频数据。数据集包含音频文件、协议文件和README文件，音频文件以flac格式存储，协议文件描述了每种清洗攻击的参数。

The ASVspoof Laundered Database is based on the ASVspoof 2019 logical access (LA) eval partition. This database is processed through five different types of additive noise at three different Signal-to-Noise ratio (SNR) levels, three types of reverberation noise, six different re-compression rates, four different resampling factors, and one type of low pass filtering, accumulating to a total of 1388.22 hours of audio data. The dataset includes features such as audio files, Speaker_Id, SYSTEM_ID, KEY, Laundering_Type, and Laundering_Param. The creators of the dataset are Hashim Ali et al., with contact information [e-mail]. The directory structure of the dataset includes folders for flac, protocols, and Readme.txt. The audio files describe the types and parameters of each laundering attack, and the protocol files provide detailed information about each laundering attack.