Detail výsledku
Spoof Diarization: "What Spoofed When" in Partially Spoofed Audio
WANG, X.
COOPER, E.
DIEZ SÁNCHEZ, M.
Landini Federico Nicolás, Ph.D., UPGM (FIT)
EVANS, N.
YAMAGISHI, J.
This paper defines Spoof Diarization as a novel task in the
Partial Spoof (PS) scenario. It aims to determine what spoofed
when, which includes not only locating spoof regions but also
clustering them according to different spoofing methods. As a
pioneering study in spoof diarization, we focus on defining the
task, establishing evaluation metrics, and proposing a bench-
mark model, namely the Countermeasure-Condition Cluster-
ing (3C) model. Utilizing this model, we first explore how
to effectively train countermeasures to support spoof diariza-
tion using three labeling schemes. We then utilize spoof lo-
calization predictions to enhance the diarization performance.
This first study reveals the high complexity of the task, even
in restricted scenarios where only a single speaker per au-
dio file and an oracle number of spoofing methods are con-
sidered. Our code is available at https://github.com/
nii-yamagishilab/PartialSpoof.
partial spoof, spoof diarization, countermeasure, clustering
@inproceedings{BUT193676,
author="ZHANG, L. and WANG, X. and COOPER, E. and DIEZ SÁNCHEZ, M. and LANDINI, F. and EVANS, N. and YAMAGISHI, J.",
title="Spoof Diarization: {"}What Spoofed When{"} in Partially Spoofed Audio",
booktitle="Proceedings of Interspeech 2024",
year="2024",
journal="Proceedings of Interspeech",
volume="2024",
number="9",
pages="502--506",
publisher="International Speech Communication Association",
address="Kos",
doi="10.21437/Interspeech.2024-1365",
issn="1990-9772",
url="https://www.isca-archive.org/interspeech_2024/zhang24j_interspeech.pdf"
}