REAL-T: Real Conversational Mixtures for Target Speaker Extraction

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

REAL-T: Real Conversational Mixtures for Target Speaker Extraction

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2025

Confidentiality

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

Article name in the collection

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

ISBN

—

ISSN

—

e-ISSN

2958-1796

Number of pages

5

Pages from-to

1923-1927

Publisher name

International Speech Communication Association

Place of publication

Rotterdam, The Netherlands

Event location

Shanghai

Event date

Oct 25, 2020

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001585350500389