PartialEdit: Identifying Partial Deepfakes in the Era of Neural Speech Editing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0199994" target="_blank" >RIV/00216305:26230/26:0199994 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-archive.org/interspeech_2025/zhang25g_interspeech.pdf" target="_blank" >https://www.isca-archive.org/interspeech_2025/zhang25g_interspeech.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/interspeech.2025-942" target="_blank" >10.21437/interspeech.2025-942</a>

Jazyk výsledku

angličtina

Název v původním jazyce

PartialEdit: Identifying Partial Deepfakes in the Era of Neural Speech Editing

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

PartialEdit: Identifying Partial Deepfakes in the Era of Neural Speech Editing

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ISBN

—

ISSN

—

e-ISSN

2958-1796

Počet stran výsledku

5

Strana od-do

5353-5357

Název nakladatele

ISCA

Místo vydání

Rotterdam, Nizozemí

Místo konání akce

Rotterdam

Datum konání akce

17. 8. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001613931400497