DiaPer: End-to-End Neural Diarization With Perceiver-Based Attractors

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F24%3APU152298" target="_blank" >RIV/00216305:26230/24:PU152298 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10584294" target="_blank" >https://ieeexplore.ieee.org/document/10584294</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TASLP.2024.3422818" target="_blank" >10.1109/TASLP.2024.3422818</a>

Jazyk výsledku

angličtina

Název v původním jazyce

DiaPer: End-to-End Neural Diarization With Perceiver-Based Attractors

Popis výsledku v původním jazyce

Until recently, the field of speaker diarization was dominated by cascaded systems. Due to their limitations, mainly re- garding overlapped speech and cumbersome pipelines, end-to-end models have gained great popularity lately. One of the most success- ful models is end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA). In this work, we replace the EDA module with a Perceiver-based one and show its advantages over EEND-EDA; namely obtaining better performance on the largely studied Callhome dataset, finding the quantity of speakers in a conversation more accurately, and faster inference time. Further- more, when exhaustively compared with other methods, our model, DiaPer, reaches remarkable performance with a very lightweight design. Besides, we perform comparisons with other works and a cascaded baseline across more than ten public wide-band datasets. Together with this publication, we release the code of DiaPer as well as models trained on public and free data.

Název v anglickém jazyce

DiaPer: End-to-End Neural Diarization With Perceiver-Based Attractors

Popis výsledku anglicky

Until recently, the field of speaker diarization was dominated by cascaded systems. Due to their limitations, mainly re- garding overlapped speech and cumbersome pipelines, end-to-end models have gained great popularity lately. One of the most success- ful models is end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA). In this work, we replace the EDA module with a Perceiver-based one and show its advantages over EEND-EDA; namely obtaining better performance on the largely studied Callhome dataset, finding the quantity of speakers in a conversation more accurately, and faster inference time. Further- more, when exhaustively compared with other methods, our model, DiaPer, reaches remarkable performance with a very lightweight design. Besides, we perform comparisons with other works and a cascaded baseline across more than ten public wide-band datasets. Together with this publication, we release the code of DiaPer as well as models trained on public and free data.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

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

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

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 periodika

IEEE Transactions on Audio, Speech, and Language Processing

ISSN

1558-7916

e-ISSN

1558-7924

Svazek periodika

32

Číslo periodika v rámci svazku

7

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

3450-3465

Kód UT WoS článku

001283673700005

EID výsledku v databázi Scopus

2-s2.0-85197558425