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
- Training police for procedural justice: An evaluation of officer attitudes, citizen attitudes, and police-citizen interactions
- Criminal Justice Interventions for Offenders With Mental Illness: Evaluation of Mental Health Courts in Bronx and Brooklyn, New York, Executive Summary
- Is the Gender Gap in Overdose Deaths (Still) Decreasing? An Examination of Opioid Deaths in Delaware, 2013–2017