Localizing Fake Segments in Speech

Partial Synthetic Detection (Psynd) dataset is a multi-speaker English corpus of 2294 utterances, approximately 13 hours English speech at 24kHz sampling rate. It is derived from LibriTTS , a read English speech corpus (all real voices) designed for TTS research. The data samples are real utterances injected with voice cloning synthetic speech. The fake parts are generated by state-of-art multi-speaker text-to-speech method and have high similarity with target speakers characterized by Global Style Token (GST) and X-Vector.部分合成检测（Partial Synthetic Detection, Psynd）数据集是一款多说话人英语语料库，包含2294条语音语句，总时长约13小时，采样率为24kHz。该数据集源自LibriTTS——一款专为文本到语音合成（Text-to-Speech, TTS）研究打造的全真人朗读英语语料库。其数据样本为注入了语音克隆合成语音的真实语音语句，其中的伪造片段由当前最先进的多说话人TTS方法生成，且与以全局风格令牌（Global Style Token, GST）和X-Vector为特征的目标说话人具有极高的相似度。

搜集汇总

背景与挑战

背景概述

该数据集是一个用于检测语音中伪造片段的英语语料库，名为Psynd，包含约13小时的多说话人语音，源自真实语音库LibriTTS。其特点是在真实语音中注入由先进TTS方法生成的合成语音，伪造部分与目标说话人高度相似，专注于部分合成检测和定位任务。