REAL-T: Real Conversational Mixtures for Target Speaker Extraction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0199411" target="_blank" >RIV/00216305:26230/26:0199411 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-archive.org/interspeech_2025/li25da_interspeech.pdf" target="_blank" >https://www.isca-archive.org/interspeech_2025/li25da_interspeech.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2025-2662" target="_blank" >10.21437/Interspeech.2025-2662</a>

Jazyk výsledku

angličtina

Název v původním jazyce

REAL-T: Real Conversational Mixtures for Target Speaker Extraction

Popis výsledku v původním jazyce

Current target speaker extraction (TSE) systems achieve remarkable performance on synthetic datasets like LibriMix and WSJMix. However, their effectiveness in real conversational scenarios, where the cocktail party problem is most prevalent, remains largely unexplored. In this paper, we conduct a comprehensive analysis of several speaker diarization datasets and introduce REAL-T, the first conversation-centric dataset specifically designed for TSE in real-world conditions. Our evaluations reveal significant performance degradation of existing TSE models on this dataset, highlighting the unaddressed complexity of real-world speech extraction. To facilitate controlled benchmarking, we define two subsets: BASE and PRIMARY, ensuring more manageable yet challenging evaluation settings.

Název v anglickém jazyce

REAL-T: Real Conversational Mixtures for Target Speaker Extraction

Popis výsledku anglicky

Current target speaker extraction (TSE) systems achieve remarkable performance on synthetic datasets like LibriMix and WSJMix. However, their effectiveness in real conversational scenarios, where the cocktail party problem is most prevalent, remains largely unexplored. In this paper, we conduct a comprehensive analysis of several speaker diarization datasets and introduce REAL-T, the first conversation-centric dataset specifically designed for TSE in real-world conditions. Our evaluations reveal significant performance degradation of existing TSE models on this dataset, highlighting the unaddressed complexity of real-world speech extraction. To facilitate controlled benchmarking, we define two subsets: BASE and PRIMARY, ensuring more manageable yet challenging evaluation settings.

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

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Annual Conference of the International Speech Communication Association Interspeech

ISBN

—

ISSN

—

e-ISSN

2958-1796

Počet stran výsledku

5

Strana od-do

1923-1927

Název nakladatele

International Speech Communication Association

Místo vydání

Rotterdam, The Netherlands

Místo konání akce

Shanghai

Datum konání akce

25. 10. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001585350500389