Result Details
PartialEdit: Identifying Partial Deepfakes in the Era of Neural Speech Editing
Tian Baotong
Zhang Lin, Ph.D.
Duan Zhiyao
Neural speech editing enables seamless partial edits to speech utterances, allowing modifications to selected content while preserving the rest of the audio unchanged. This useful technique, however, also poses new risks of deepfakes. To encourage research on detecting such partially edited deepfake speech, we introduce PartialEdit, a deepfake speech dataset
curated using advanced neural editing techniques. We explore both detection and localization tasks on PartialEdit. Our experiments reveal that models trained on the existing Partial-Spoof dataset fail to detect partially edited speech generated by neural speech editing models. As recent speech editing models almost all involve neural audio codecs, we also provide insights into the artifacts the model learned on detecting these deepfakes. Further information about the PartialEdit dataset and audio samples can be found on the project page: https:
//yzyouzhang.com/PartialEdit/index.html.
speech deepfake detection, neural speech editing, partial deepfake audio, anti-spoofing, dataset
@inproceedings{BUT199994,
author="{} and {} and Lin {Zhang} and {}",
title="PartialEdit: Identifying Partial Deepfakes in the Era of Neural Speech Editing",
booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
year="2025",
journal="Interspeech",
pages="5353--5357",
publisher="ISCA",
address="Rotterdam, Nizozemí",
doi="10.21437/interspeech.2025-942",
url="https://www.isca-archive.org/interspeech_2025/zhang25g_interspeech.pdf"
}