datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
styletransfer_audionew_data_styletransfervoice_cloning_style_transfer
Voice "Cloning" is Style Transfer — Audio Dataset
Companion dataset for the preprint
"Voice 'Cloning' is Style Transfer" (Zhou, Bianchi, Bartelds, Pot, Kwon, Zou; 2026).
Code, notebooks, and reproduction figures live at
github.com/kzhou-cloud/voice-cloning-public.
🎧 Listen to a small set of paired examples on the
project page.
What's in here
Split
# files
Description
original
699
QC-validated human recordings of the Grandfather Passage from 86 non-native… See the full description on the dataset page: https://huggingface.co/datasets/kzhou/voice_cloning_style_transfer.new_data_styletransfer3styletransfer_audio_db