|Title:||Localizing Fake Segments in Speech||Creators:||SIM MONG CHENG, TERENCE
|NUS Contact:||Terence, Mong Cheng Sim||Subject:||Computer Science||DOI:||doi:10.25540/4VMK-AYPV||Description:||
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.
|Related Publications:||Localizing Fake Segments in Speech||Citation:||When using this data, please cite the original publication and also the dataset.
||License:||CC0 1.0 Universal
|Appears in Collections:||Other Dataset|
Show full item record
This item is licensed under a Creative Commons License