Spoof Diarization: "What Spoofed When" in Partially Spoofed Audio

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F24%3APU154934" target="_blank" >RIV/00216305:26230/24:PU154934 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-archive.org/interspeech_2024/zhang24j_interspeech.pdf" target="_blank" >https://www.isca-archive.org/interspeech_2024/zhang24j_interspeech.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2024-1365" target="_blank" >10.21437/Interspeech.2024-1365</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Spoof Diarization: "What Spoofed When" in Partially Spoofed Audio

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Spoof Diarization: "What Spoofed When" in Partially Spoofed Audio

Popis výsledku anglicky

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.

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

<a href="/cs/project/VJ01010108" target="_blank" >VJ01010108: Robustní zpracování nahrávek pro operativu a bezpečnost</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of Interspeech 2024

ISBN

—

ISSN

1990-9772

e-ISSN

—

Počet stran výsledku

5

Strana od-do

502-506

Název nakladatele

International Speech Communication Association

Místo vydání

Kos

Místo konání akce

Kos

Datum konání akce

1. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—