DiaPer: End-to-End Neural Diarization With Perceiver-Based Attractors
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
DiaPer: End-to-End Neural Diarization With Perceiver-Based Attractors
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
IEEE Transactions on Audio, Speech, and Language Processing
ISSN
1558-7916
e-ISSN
1558-7924
Volume of the periodical
32
Issue of the periodical within the volume
7
Country of publishing house
US - UNITED STATES
Number of pages
16
Pages from-to
3450-3465
UT code for WoS article
001283673700005
EID of the result in the Scopus database
2-s2.0-85197558425