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 PartialSpoof 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.
(Publisher abstract provided.)
Similar Publications
- Cumulative determinants of adolescent health indicators: the effects of social and structural determinants of health and child sexual abuse on overdose and suicide attempt
- Parental Hostility as a Moderator of the Criminogenic Effect of Parental Criminal Justice Contact Among Youth Adjudicated of Serious Offenses
- Bone Mineral Density Adult Age Estimation in Forensic Anthropology: A Test of the DXAGE Application