Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149424" target="_blank" >RIV/00216305:26230/23:PU149424 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10097049" target="_blank" >https://ieeexplore.ieee.org/document/10097049</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP49357.2023.10097049" target="_blank" >10.1109/ICASSP49357.2023.10097049</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization

Popis výsledku v původním jazyce

End-to-end diarization presents an attractive alternative to standard cascaded diarization systems because a single system can handle all aspects of the task at once. Many flavors of end-to-end models have been proposed but all of them require (so far non-existing) large amounts of annotated data for training. The compromise solution consists in generating synthetic data and the recently proposed simulated conversations (SC) have shown remarkable improvements over the original simulated mixtures (SM). In this work, we create SC with multiple speakers per conversation and show that they allow for substantially better performance than SM, also reducing the dependence on a fine-tuning stage. We also create SC with wide-band public audio sources and present an analysis on several evaluation sets. Together with this publication, we release the recipes for generating such data and models trained on public sets as well as the implementation to efficiently handle multiple speakers per conversation and an auxiliary voice activity detection loss.

Název v anglickém jazyce

Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization

Popis výsledku anglicky

End-to-end diarization presents an attractive alternative to standard cascaded diarization systems because a single system can handle all aspects of the task at once. Many flavors of end-to-end models have been proposed but all of them require (so far non-existing) large amounts of annotated data for training. The compromise solution consists in generating synthetic data and the recently proposed simulated conversations (SC) have shown remarkable improvements over the original simulated mixtures (SM). In this work, we create SC with multiple speakers per conversation and show that they allow for substantially better performance than SM, also reducing the dependence on a fine-tuning stage. We also create SC with wide-band public audio sources and present an analysis on several evaluation sets. Together with this publication, we release the recipes for generating such data and models trained on public sets as well as the implementation to efficiently handle multiple speakers per conversation and an auxiliary voice activity detection loss.

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

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

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of ICASSP 2023

ISBN

978-1-7281-6327-7

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

1-5

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Rhodes Island

Místo konání akce

Rhodes Island, Greece

Datum konání akce

4. 6. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—